Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Shalabh Bhatnagar
@article{DBLP:journals/icl/BaratJB24,
author = {Arghyadeep Barat and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Energy Management in a Cooperative Energy Harvesting Wireless Sensor
Network},
journal = {{IEEE} Commun. Lett.},
volume = {28},
number = {1},
pages = {243--247},
year = {2024},
url = {https://doi.org/10.1109/LCOMM.2023.3335143},
doi = {10.1109/LCOMM.2023.3335143},
timestamp = {Fri, 26 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/icl/BaratJB24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isgt/VivekDB24,
author = {V. P. Vivek and
Raghuram Bharadwaj Diddigi and
Shalabh Bhatnagar},
title = {Dynamic Energy Management in Competing Microgrids using Reinforcement
Learning},
booktitle = {{IEEE} Power {\&} Energy Society Innovative Smart Grid Technologies
Conference, {ISGT} 2024, Washington, DC, USA, February 19-22, 2024},
pages = {1--5},
publisher = {{IEEE}},
year = {2024},
url = {https://doi.org/10.1109/ISGT59692.2024.10454198},
doi = {10.1109/ISGT59692.2024.10454198},
timestamp = {Wed, 13 Mar 2024 18:04:53 +0100},
biburl = {https://dblp.org/rec/conf/isgt/VivekDB24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-01371,
author = {Prashansa Panda and
Shalabh Bhatnagar},
title = {Critic-Actor for Average Reward MDPs with Function Approximation:
{A} Finite-Time Analysis},
journal = {CoRR},
volume = {abs/2402.01371},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.01371},
doi = {10.48550/ARXIV.2402.01371},
eprinttype = {arXiv},
eprint = {2402.01371},
timestamp = {Fri, 09 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-01371.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csysl/BhatnagarBG23,
author = {Shalabh Bhatnagar and
Vivek S. Borkar and
Soumyajit Guin},
title = {Actor-Critic or Critic-Actor? {A} Tale of Two Time Scales},
journal = {{IEEE} Control. Syst. Lett.},
volume = {7},
pages = {2671--2676},
year = {2023},
url = {https://doi.org/10.1109/LCSYS.2023.3288931},
doi = {10.1109/LCSYS.2023.3288931},
timestamp = {Fri, 21 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/csysl/BhatnagarBG23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/GuinB23,
author = {Soumyajit Guin and
Shalabh Bhatnagar},
title = {A Policy Gradient Approach for Finite Horizon Constrained Markov Decision
Processes},
booktitle = {62nd {IEEE} Conference on Decision and Control, {CDC} 2023, Singapore,
December 13-15, 2023},
pages = {3353--3359},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CDC49753.2023.10383413},
doi = {10.1109/CDC49753.2023.10383413},
timestamp = {Mon, 29 Jan 2024 17:30:32 +0100},
biburl = {https://dblp.org/rec/conf/cdc/GuinB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ciss/BhatnagarA23,
author = {Shalabh Bhatnagar and
Prashanth L. A.},
title = {Generalized Simultaneous Perturbation Stochastic Approximation with
Reduced Estimator Bias},
booktitle = {57th Annual Conference on Information Sciences and Systems, {CISS}
2023, Baltimore, MD, USA, March 22-24, 2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CISS56502.2023.10089720},
doi = {10.1109/CISS56502.2023.10089720},
timestamp = {Sat, 22 Apr 2023 16:25:53 +0200},
biburl = {https://dblp.org/rec/conf/ciss/BhatnagarA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SaxenaKKB23,
author = {Naman Saxena and
Subhojyoti Khastagir and
Shishir Kolathaya and
Shalabh Bhatnagar},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Off-Policy Average Reward Actor-Critic with Deterministic Policy Search},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {30130--30203},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/saxena23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/SaxenaKKB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/KarumanchiDJB23,
author = {Sambhu H. Karumanchi and
Raghuram Bharadwaj Diddigi and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Autonomous {UAV} Navigation in Complex Environments using Human Feedback},
booktitle = {32nd {IEEE} International Conference on Robot and Human Interactive
Communication, {RO-MAN} 2023, Busan, Republic of Korea, August 28-31,
2023},
pages = {499--506},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/RO-MAN57019.2023.10309494},
doi = {10.1109/RO-MAN57019.2023.10309494},
timestamp = {Thu, 23 Nov 2023 21:16:36 +0100},
biburl = {https://dblp.org/rec/conf/ro-man/KarumanchiDJB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-07068,
author = {Lakshmi Mandal and
Shalabh Bhatnagar},
title = {n-Step Temporal Difference Learning with Optimal n},
journal = {CoRR},
volume = {abs/2303.07068},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.07068},
doi = {10.48550/ARXIV.2303.07068},
eprinttype = {arXiv},
eprint = {2303.07068},
timestamp = {Thu, 16 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-07068.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-10951,
author = {Mizhaan Prajit Maniyar and
Akash Mondal and
Prashanth L. A. and
Shalabh Bhatnagar},
title = {A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning},
journal = {CoRR},
volume = {abs/2304.10951},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.10951},
doi = {10.48550/ARXIV.2304.10951},
eprinttype = {arXiv},
eprint = {2304.10951},
timestamp = {Tue, 02 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-10951.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-12125,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar and
Naman Saxena},
title = {A Framework for Provably Stable and Consistent Training of Deep Feedforward
Networks},
journal = {CoRR},
volume = {abs/2305.12125},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.12125},
doi = {10.48550/ARXIV.2305.12125},
eprinttype = {arXiv},
eprint = {2305.12125},
timestamp = {Fri, 26 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-12125.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-12239,
author = {Naman Saxena and
Subhojyoti Khastagir and
Shishir Kolathaya and
Shalabh Bhatnagar},
title = {Off-Policy Average Reward Actor-Critic with Deterministic Policy Search},
journal = {CoRR},
volume = {abs/2305.12239},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.12239},
doi = {10.48550/ARXIV.2305.12239},
eprinttype = {arXiv},
eprint = {2305.12239},
timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-12239.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-05000,
author = {Shalabh Bhatnagar},
title = {The Reinforce Policy Gradient Algorithm Revisited},
journal = {CoRR},
volume = {abs/2310.05000},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.05000},
doi = {10.48550/ARXIV.2310.05000},
eprinttype = {arXiv},
eprint = {2310.05000},
timestamp = {Fri, 20 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-05000.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-05911,
author = {Arghyadeep Barat and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Energy Management in a Cooperative Energy Harvesting Wireless Sensor
Network},
journal = {CoRR},
volume = {abs/2310.05911},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.05911},
doi = {10.48550/ARXIV.2310.05911},
eprinttype = {arXiv},
eprint = {2310.05911},
timestamp = {Thu, 23 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-05911.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-16363,
author = {Prashansa Panda and
Shalabh Bhatnagar},
title = {Finite Time Analysis of Constrained Actor Critic and Constrained Natural
Actor Critic Algorithms},
journal = {CoRR},
volume = {abs/2310.16363},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.16363},
doi = {10.48550/ARXIV.2310.16363},
eprinttype = {arXiv},
eprint = {2310.16363},
timestamp = {Tue, 31 Oct 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-16363.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2311-11789,
author = {Lakshmi Mandal and
Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {Approximate Linear Programming and Decentralized Policy Improvement
in Cooperative Multi-agent Markov Decision Processes},
journal = {CoRR},
volume = {abs/2311.11789},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2311.11789},
doi = {10.48550/ARXIV.2311.11789},
eprinttype = {arXiv},
eprint = {2311.11789},
timestamp = {Thu, 23 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2311-11789.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/RamaswamyB22,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Analyzing Approximate Value Iteration Algorithms},
journal = {Math. Oper. Res.},
volume = {47},
number = {3},
pages = {2138--2159},
year = {2022},
url = {https://doi.org/10.1287/moor.2021.1202},
doi = {10.1287/MOOR.2021.1202},
timestamp = {Mon, 05 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mor/RamaswamyB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/KamanchiDB22,
author = {Chandramouli Kamanchi and
Raghuram Bharadwaj Diddigi and
Shalabh Bhatnagar},
title = {Generalized Second-Order Value Iteration in Markov Decision Processes},
journal = {{IEEE} Trans. Autom. Control.},
volume = {67},
number = {8},
pages = {4241--4247},
year = {2022},
url = {https://doi.org/10.1109/TAC.2021.3112851},
doi = {10.1109/TAC.2021.3112851},
timestamp = {Mon, 08 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/KamanchiDB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/DiddigiKB22,
author = {Raghuram Bharadwaj Diddigi and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum
Stochastic Games},
journal = {{IEEE} Trans. Autom. Control.},
volume = {67},
number = {9},
pages = {4816--4823},
year = {2022},
url = {https://doi.org/10.1109/TAC.2022.3159453},
doi = {10.1109/TAC.2022.3159453},
timestamp = {Sat, 10 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/DiddigiKB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/DebB22,
author = {Rohan Deb and
Shalabh Bhatnagar},
title = {Gradient Temporal Difference with Momentum: Stability and Convergence},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {6488--6496},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i6.20601},
doi = {10.1609/AAAI.V36I6.20601},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/DebB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/DebGB22,
author = {Rohan Deb and
Meet Gandhi and
Shalabh Bhatnagar},
title = {Schedule Based Temporal Difference Algorithms},
booktitle = {58th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2022, Monticello, IL, USA, September 27-30, 2022},
pages = {1--6},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/Allerton49937.2022.9929388},
doi = {10.1109/ALLERTON49937.2022.9929388},
timestamp = {Fri, 11 Nov 2022 16:53:12 +0100},
biburl = {https://dblp.org/rec/conf/allerton/DebGB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icaart/Shanmugasundaram22a,
author = {Priya Shanmugasundaram and
Shalabh Bhatnagar},
editor = {Ana Paula Rocha and
Luc Steels and
H. Jaap van den Herik},
title = {Co-operative Multi-agent Twin Delayed {DDPG} for Robust Phase Duration
Optimization of Large Road Networks},
booktitle = {Agents and Artificial Intelligence - 14th International Conference,
{ICAART} 2022, Virtual Event, February 3-5, 2022, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {13786},
pages = {122--142},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-3-031-22953-4\_6},
doi = {10.1007/978-3-031-22953-4\_6},
timestamp = {Mon, 26 Jun 2023 20:44:19 +0200},
biburl = {https://dblp.org/rec/conf/icaart/Shanmugasundaram22a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icaart/Shanmugasundaram22,
author = {Priya Shanmugasundaram and
Shalabh Bhatnagar},
editor = {Ana Paula Rocha and
Luc Steels and
H. Jaap van den Herik},
title = {Robust Traffic Signal Timing Control using Multiagent Twin Delayed
Deep Deterministic Policy Gradients},
booktitle = {Proceedings of the 14th International Conference on Agents and Artificial
Intelligence, {ICAART} 2022, Volume 2, Online Streaming, February
3-5, 2022},
pages = {477--485},
publisher = {{SCITEPRESS}},
year = {2022},
url = {https://doi.org/10.5220/0010889300003116},
doi = {10.5220/0010889300003116},
timestamp = {Tue, 06 Jun 2023 14:58:00 +0200},
biburl = {https://dblp.org/rec/conf/icaart/Shanmugasundaram22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/MishraSGKLSSBK22,
author = {Utkarsh A. Mishra and
Soumya R. Samineni and
Prakhar Goel and
Chandravaran Kunjeti and
Himanshu Lodha and
Aman Singh and
Aditya Sagi and
Shalabh Bhatnagar and
Shishir Kolathaya},
title = {Dynamic Mirror Descent based Model Predictive Control for Accelerating
Robot Learning},
booktitle = {2022 International Conference on Robotics and Automation, {ICRA} 2022,
Philadelphia, PA, USA, May 23-27, 2022},
pages = {1631--1637},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICRA46639.2022.9812089},
doi = {10.1109/ICRA46639.2022.9812089},
timestamp = {Wed, 20 Jul 2022 18:22:23 +0200},
biburl = {https://dblp.org/rec/conf/icra/MishraSGKLSSBK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/DiddigiJJB22,
author = {Raghuram Bharadwaj Diddigi and
Prateek Jain and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2022, Padua,
Italy, July 18-23, 2022},
pages = {1--10},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IJCNN55064.2022.9892303},
doi = {10.1109/IJCNN55064.2022.9892303},
timestamp = {Mon, 10 Oct 2022 17:40:09 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/DiddigiJJB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/JayantB22,
author = {Ashish Kumar Jayant and
Shalabh Bhatnagar},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Model-based Safe Deep Reinforcement Learning via a Constrained Proximal
Policy Optimization Algorithm},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference
on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans,
LA, USA, November 28 - December 9, 2022},
year = {2022},
url = {http://papers.nips.cc/paper\_files/paper/2022/hash/9a8eb202c060b7d81f5889631cbcd47e-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/JayantB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/PadakandlaJGB22,
author = {Sindhu Padakandla and
Prabuchandran K. J. and
Sourav Ganguly and
Shalabh Bhatnagar},
title = {Data Efficient Safe Reinforcement Learning},
booktitle = {{IEEE} International Conference on Systems, Man, and Cybernetics,
{SMC} 2022, Prague, Czech Republic, October 9-12, 2022},
pages = {1167--1172},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SMC53654.2022.9945313},
doi = {10.1109/SMC53654.2022.9945313},
timestamp = {Thu, 01 Dec 2022 15:59:35 +0100},
biburl = {https://dblp.org/rec/conf/smc/PadakandlaJGB22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-00286,
author = {Arun Raman and
Keerthan Shagrithaya and
Shalabh Bhatnagar},
title = {Reinforcement Learning for Task Specifications with Action-Constraints},
journal = {CoRR},
volume = {abs/2201.00286},
year = {2022},
url = {https://arxiv.org/abs/2201.00286},
eprinttype = {arXiv},
eprint = {2201.00286},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-00286.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2208-00290,
author = {Akash Mondal and
Prashanth L. A. and
Shalabh Bhatnagar},
title = {A Gradient Smoothed Functional Algorithm with Truncated Cauchy Random
Perturbations for Stochastic Optimization},
journal = {CoRR},
volume = {abs/2208.00290},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2208.00290},
doi = {10.48550/ARXIV.2208.00290},
eprinttype = {arXiv},
eprint = {2208.00290},
timestamp = {Wed, 10 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2208-00290.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-04470,
author = {Shalabh Bhatnagar and
Vivek S. Borkar and
Soumyajit Guin},
title = {Actor-Critic or Critic-Actor? {A} Tale of Two Time Scales},
journal = {CoRR},
volume = {abs/2210.04470},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.04470},
doi = {10.48550/ARXIV.2210.04470},
eprinttype = {arXiv},
eprint = {2210.04470},
timestamp = {Wed, 12 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-04470.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-04527,
author = {Soumyajit Guin and
Shalabh Bhatnagar},
title = {A policy gradient approach for Finite Horizon Constrained Markov Decision
Processes},
journal = {CoRR},
volume = {abs/2210.04527},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.04527},
doi = {10.48550/ARXIV.2210.04527},
eprinttype = {arXiv},
eprint = {2210.04527},
timestamp = {Thu, 13 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-04527.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-07573,
author = {Ashish Kumar Jayant and
Shalabh Bhatnagar},
title = {Model-based Safe Deep Reinforcement Learning via a Constrained Proximal
Policy Optimization Algorithm},
journal = {CoRR},
volume = {abs/2210.07573},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.07573},
doi = {10.48550/ARXIV.2210.07573},
eprinttype = {arXiv},
eprint = {2210.07573},
timestamp = {Tue, 18 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-07573.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-10477,
author = {Shalabh Bhatnagar and
Prashanth L. A.},
title = {Generalized Simultaneous Perturbation Stochastic Approximation with
Reduced Estimator Bias},
journal = {CoRR},
volume = {abs/2212.10477},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.10477},
doi = {10.48550/ARXIV.2212.10477},
eprinttype = {arXiv},
eprint = {2212.10477},
timestamp = {Wed, 04 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-10477.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/apin/JPKB21,
author = {Prabuchandran K. J. and
Santosh Penubothula and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {Novel First Order Bayesian Optimization with an Application to Reinforcement
Learning},
journal = {Appl. Intell.},
volume = {51},
number = {3},
pages = {1565--1579},
year = {2021},
url = {https://doi.org/10.1007/s10489-020-01896-w},
doi = {10.1007/S10489-020-01896-W},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/apin/JPKB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scl/KarmakarB21,
author = {Prasenjit Karmakar and
Shalabh Bhatnagar},
title = {On tight bounds for function approximation error in risk-sensitive
reinforcement learning},
journal = {Syst. Control. Lett.},
volume = {150},
pages = {104899},
year = {2021},
url = {https://doi.org/10.1016/j.sysconle.2021.104899},
doi = {10.1016/J.SYSCONLE.2021.104899},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scl/KarmakarB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/RamaswamyBQ21,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar and
Daniel E. Quevedo},
title = {Asynchronous Stochastic Approximations With Asymptotically Biased
Errors and Deep Multiagent Learning},
journal = {{IEEE} Trans. Autom. Control.},
volume = {66},
number = {9},
pages = {3969--3983},
year = {2021},
url = {https://doi.org/10.1109/TAC.2020.3026269},
doi = {10.1109/TAC.2020.3026269},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/RamaswamyBQ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/KarmakarB21,
author = {Prasenjit Karmakar and
Shalabh Bhatnagar},
title = {Stochastic Approximation With Iterate-Dependent Markov Noise Under
Verifiable Conditions in Compact State Space With the Stability of
Iterates Not Ensured},
journal = {{IEEE} Trans. Autom. Control.},
volume = {66},
number = {12},
pages = {5941--5954},
year = {2021},
url = {https://doi.org/10.1109/TAC.2021.3057299},
doi = {10.1109/TAC.2021.3057299},
timestamp = {Wed, 15 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tac/KarmakarB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tits/SinglaPB21,
author = {Abhik Singla and
Sindhu Padakandla and
Shalabh Bhatnagar},
title = {Memory-Based Deep Reinforcement Learning for Obstacle Avoidance in
{UAV} With Limited Environment Knowledge},
journal = {{IEEE} Trans. Intell. Transp. Syst.},
volume = {22},
number = {1},
pages = {107--118},
year = {2021},
url = {https://doi.org/10.1109/TITS.2019.2954952},
doi = {10.1109/TITS.2019.2954952},
timestamp = {Tue, 02 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tits/SinglaPB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/ParnikaDDB21,
author = {P. Parnika and
Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Attention Actor-Critic Algorithm for Multi-Agent Constrained Co-operative
Reinforcement Learning},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {1616--1618},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1616.pdf},
doi = {10.5555/3463952.3464178},
timestamp = {Wed, 20 Jul 2022 17:03:47 +0200},
biburl = {https://dblp.org/rec/conf/atal/ParnikaDDB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-02349,
author = {P. Parnika and
Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {Attention Actor-Critic algorithm for Multi-Agent Constrained Co-operative
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2101.02349},
year = {2021},
url = {https://arxiv.org/abs/2101.02349},
eprinttype = {arXiv},
eprint = {2101.02349},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-02349.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-10017,
author = {Raghuram Bharadwaj Diddigi and
Prateek Jain and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Neural Network Compatible Off-Policy Natural Actor-Critic Algorithm},
journal = {CoRR},
volume = {abs/2110.10017},
year = {2021},
url = {https://arxiv.org/abs/2110.10017},
eprinttype = {arXiv},
eprint = {2110.10017},
timestamp = {Mon, 25 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-10017.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-15093,
author = {Vivek VP and
Shalabh Bhatnagar},
title = {Finite Horizon Q-learning: Stability, Convergence and Simulations},
journal = {CoRR},
volume = {abs/2110.15093},
year = {2021},
url = {https://arxiv.org/abs/2110.15093},
eprinttype = {arXiv},
eprint = {2110.15093},
timestamp = {Tue, 02 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-15093.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-11004,
author = {Rohan Deb and
Shalabh Bhatnagar},
title = {Gradient Temporal Difference with Momentum: Stability and Convergence},
journal = {CoRR},
volume = {abs/2111.11004},
year = {2021},
url = {https://arxiv.org/abs/2111.11004},
eprinttype = {arXiv},
eprint = {2111.11004},
timestamp = {Fri, 26 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-11004.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-11768,
author = {Rohan Deb and
Meet Gandhi and
Shalabh Bhatnagar},
title = {Schedule Based Temporal Difference Algorithms},
journal = {CoRR},
volume = {abs/2111.11768},
year = {2021},
url = {https://arxiv.org/abs/2111.11768},
eprinttype = {arXiv},
eprint = {2111.11768},
timestamp = {Fri, 26 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-11768.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-02999,
author = {Utkarsh A. Mishra and
Soumya R. Samineni and
Prakhar Goel and
Chandravaran Kunjeti and
Himanshu Lodha and
Aman Singh and
Aditya Sagi and
Shalabh Bhatnagar and
Shishir Kolathaya},
title = {Dynamic Mirror Descent based Model Predictive Control for Accelerating
Robot Learning},
journal = {CoRR},
volume = {abs/2112.02999},
year = {2021},
url = {https://arxiv.org/abs/2112.02999},
eprinttype = {arXiv},
eprint = {2112.02999},
timestamp = {Wed, 08 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-02999.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-03515,
author = {Rohan Deb and
Shalabh Bhatnagar},
title = {N-Timescale Stochastic Approximation: Stability and Convergence},
journal = {CoRR},
volume = {abs/2112.03515},
year = {2021},
url = {https://arxiv.org/abs/2112.03515},
eprinttype = {arXiv},
eprint = {2112.03515},
timestamp = {Mon, 13 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-03515.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/apin/PadakandlaJB20,
author = {Sindhu Padakandla and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Reinforcement learning algorithm for non-stationary environments},
journal = {Appl. Intell.},
volume = {50},
number = {11},
pages = {3590--3606},
year = {2020},
url = {https://doi.org/10.1007/s10489-020-01758-5},
doi = {10.1007/S10489-020-01758-5},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/apin/PadakandlaJB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csysl/KamanchiDB20,
author = {Chandramouli Kamanchi and
Raghuram Bharadwaj Diddigi and
Shalabh Bhatnagar},
title = {Successive Over-Relaxation {\textdollar}\{Q\}{\textdollar} -Learning},
journal = {{IEEE} Control. Syst. Lett.},
volume = {4},
number = {1},
pages = {55--60},
year = {2020},
url = {https://doi.org/10.1109/LCSYS.2019.2921158},
doi = {10.1109/LCSYS.2019.2921158},
timestamp = {Tue, 24 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csysl/KamanchiDB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csysl/JohnKB20,
author = {Indu John and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {Generalized Speedy Q-Learning},
journal = {{IEEE} Control. Syst. Lett.},
volume = {4},
number = {3},
pages = {524--529},
year = {2020},
url = {https://doi.org/10.1109/LCSYS.2020.2970555},
doi = {10.1109/LCSYS.2020.2970555},
timestamp = {Tue, 16 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/csysl/JohnKB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/YajiB20,
author = {Vinayaka G. Yaji and
Shalabh Bhatnagar},
title = {Stochastic Recursive Inclusions in Two Timescales with Nonadditive
Iterate-Dependent Markov Noise},
journal = {Math. Oper. Res.},
volume = {45},
number = {4},
pages = {1405--1444},
year = {2020},
url = {https://doi.org/10.1287/moor.2019.1037},
doi = {10.1287/MOOR.2019.1037},
timestamp = {Thu, 16 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/YajiB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/YajiB20,
author = {Vinayaka G. Yaji and
Shalabh Bhatnagar},
title = {Analysis of Stochastic Approximation Schemes With Set-Valued Maps
in the Absence of a Stability Guarantee and Their Stabilization},
journal = {{IEEE} Trans. Autom. Control.},
volume = {65},
number = {3},
pages = {1100--1115},
year = {2020},
url = {https://doi.org/10.1109/TAC.2019.2916688},
doi = {10.1109/TAC.2019.2916688},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/YajiB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/ABBFM20,
author = {Prashanth L. A. and
Shalabh Bhatnagar and
Nirav Bhavsar and
Michael C. Fu and
Steven I. Marcus},
title = {Random Directions Stochastic Approximation With Deterministic Perturbations},
journal = {{IEEE} Trans. Autom. Control.},
volume = {65},
number = {6},
pages = {2450--2465},
year = {2020},
url = {https://doi.org/10.1109/TAC.2019.2930821},
doi = {10.1109/TAC.2019.2930821},
timestamp = {Tue, 16 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/ABBFM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/DharmavaramRB20,
author = {Akshay Dharmavaram and
Matthew Riemer and
Shalabh Bhatnagar},
title = {Hierarchical Average Reward Policy Gradient Algorithms (Student Abstract)},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {13777--13778},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i10.7160},
doi = {10.1609/AAAI.V34I10.7160},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/DharmavaramRB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/PaigwarKTKVJBGA20,
author = {Kartik Paigwar and
Lokesh Krishna and
Sashank Tirumala and
Naman Khetan and
Aditya Varma and
Ashish Joglekar and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
editor = {Jens Kober and
Fabio Ramos and
Claire J. Tomlin},
title = {Robust Quadrupedal Locomotion on Sloped Terrains: {A} Linear Policy
Approach},
booktitle = {4th Conference on Robot Learning, CoRL 2020, 16-18 November 2020,
Virtual Event / Cambridge, MA, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {155},
pages = {2257--2267},
publisher = {{PMLR}},
year = {2020},
url = {https://proceedings.mlr.press/v155/paigwar21a.html},
timestamp = {Tue, 18 Oct 2022 08:35:37 +0200},
biburl = {https://dblp.org/rec/conf/corl/PaigwarKTKVJBGA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/DiddigiKB20,
author = {Raghuram Bharadwaj Diddigi and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
editor = {Giuseppe De Giacomo and
Alejandro Catal{\'{a}} and
Bistra Dilkina and
Michela Milano and
Sen{\'{e}}n Barro and
Alberto Bugar{\'{\i}}n and
J{\'{e}}r{\^{o}}me Lang},
title = {A Convergent Off-Policy Temporal Difference Algorithm},
booktitle = {{ECAI} 2020 - 24th European Conference on Artificial Intelligence,
29 August-8 September 2020, Santiago de Compostela, Spain, August
29 - September 8, 2020 - Including 10th Conference on Prestigious
Applications of Artificial Intelligence {(PAIS} 2020)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {325},
pages = {1103--1110},
publisher = {{IOS} Press},
year = {2020},
url = {https://doi.org/10.3233/FAIA200207},
doi = {10.3233/FAIA200207},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecai/DiddigiKB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/JohnB20,
author = {Indu John and
Shalabh Bhatnagar},
title = {Deep Reinforcement Learning with Successive Over-Relaxation and its
Application in Autoscaling Cloud Resources},
booktitle = {2020 International Joint Conference on Neural Networks, {IJCNN} 2020,
Glasgow, United Kingdom, July 19-24, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/IJCNN48605.2020.9206598},
doi = {10.1109/IJCNN48605.2020.9206598},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/JohnB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isgteurope/NayakECDRSDB20,
author = {Shravan Nayak and
Chanakya Ajit Ekbote and
Annanya Pratap Singh Chauhan and
Raghuram Bharadwaj Diddigi and
Prishita Ray and
Abhinava Sikdar and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {Stochastic Game Frameworks for Efficient Energy Management in Microgrid
Networks},
booktitle = {{IEEE} {PES} Innovative Smart Grid Technologies Europe, {ISGT} Europe
2020, Delft, The Netherlands, October 26-28, 2020},
pages = {116--120},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ISGT-Europe47291.2020.9248952},
doi = {10.1109/ISGT-EUROPE47291.2020.9248952},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isgteurope/NayakECDRSDB20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pimrc/Padakandla0B20,
author = {Sindhu Padakandla and
Shilpa Rao and
Shalabh Bhatnagar},
title = {Learning-Based Resource Allocation in Industrial IoT Systems},
booktitle = {31st {IEEE} Annual International Symposium on Personal, Indoor and
Mobile Radio Communications, {PIMRC} 2020, London, United Kingdom,
August 31 - September 3, 2020},
pages = {1--7},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/PIMRC48278.2020.9217170},
doi = {10.1109/PIMRC48278.2020.9217170},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pimrc/Padakandla0B20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/TirumalaGPSJBGA20,
author = {Sashank Tirumala and
Sagar Venkatesh Gubbi and
Kartik Paigwar and
Aditya Sagi and
Ashish Joglekar and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Learning Stable Manoeuvres in Quadruped Robots from Expert Demonstrations},
booktitle = {29th {IEEE} International Conference on Robot and Human Interactive
Communication, {RO-MAN} 2020, Naples, Italy, August 31 - September
4, 2020},
pages = {1107--1112},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/RO-MAN47096.2020.9223511},
doi = {10.1109/RO-MAN47096.2020.9223511},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ro-man/TirumalaGPSJBGA20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-02084,
author = {Shravan Nayak and
Chanakya Ajit Ekbote and
Annanya Pratap Singh Chauhan and
Raghuram Bharadwaj Diddigi and
Prishita Ray and
Abhinava Sikdar and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {A Stochastic Game Framework for Efficient Energy Management in Microgrid
Networks},
journal = {CoRR},
volume = {abs/2002.02084},
year = {2020},
url = {https://arxiv.org/abs/2002.02084},
eprinttype = {arXiv},
eprint = {2002.02084},
timestamp = {Mon, 10 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-02084.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-14290,
author = {Sashank Tirumala and
Sagar Venkatesh Gubbi and
Kartik Paigwar and
Aditya Sagi and
Ashish Joglekar and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Learning Stable Manoeuvres in Quadruped Robots from Expert Demonstrations},
journal = {CoRR},
volume = {abs/2007.14290},
year = {2020},
url = {https://arxiv.org/abs/2007.14290},
eprinttype = {arXiv},
eprint = {2007.14290},
timestamp = {Mon, 03 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-14290.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-00821,
author = {Meet Gandhi and
Atreyee Kundu and
Shalabh Bhatnagar},
title = {A reinforcement learning approach to hybrid control design},
journal = {CoRR},
volume = {abs/2009.00821},
year = {2020},
url = {https://arxiv.org/abs/2009.00821},
eprinttype = {arXiv},
eprint = {2009.00821},
timestamp = {Wed, 16 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-00821.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-06142,
author = {Dhuruva Priyan G. M and
Abhik Singla and
Shalabh Bhatnagar},
title = {Hindsight Experience Replay with Kronecker Product Approximate Curvature},
journal = {CoRR},
volume = {abs/2010.06142},
year = {2020},
url = {https://arxiv.org/abs/2010.06142},
eprinttype = {arXiv},
eprint = {2010.06142},
timestamp = {Tue, 20 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-06142.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-16342,
author = {Kartik Paigwar and
Lokesh Krishna and
Sashank Tirumala and
Naman Khetan and
Aditya Sagi and
Ashish Joglekar and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Robust Quadrupedal Locomotion on Sloped Terrains: {A} Linear Policy
Approach},
journal = {CoRR},
volume = {abs/2010.16342},
year = {2020},
url = {https://arxiv.org/abs/2010.16342},
eprinttype = {arXiv},
eprint = {2010.16342},
timestamp = {Tue, 03 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-16342.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csysl/KamanchiDJB19,
author = {Chandramouli Kamanchi and
Raghuram Bharadwaj Diddigi and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {An Online Sample-Based Method for Mode Estimation Using {ODE} Analysis
of Stochastic Approximation Algorithms},
journal = {{IEEE} Control. Syst. Lett.},
volume = {3},
number = {3},
pages = {697--702},
year = {2019},
url = {https://doi.org/10.1109/LCSYS.2019.2916467},
doi = {10.1109/LCSYS.2019.2916467},
timestamp = {Tue, 24 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csysl/KamanchiDJB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/RamaswamyB19,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Stability of Stochastic Approximations With "Controlled Markov"
Noise and Temporal Difference Learning},
journal = {{IEEE} Trans. Autom. Control.},
volume = {64},
number = {6},
pages = {2614--2620},
year = {2019},
url = {https://doi.org/10.1109/TAC.2018.2874687},
doi = {10.1109/TAC.2018.2874687},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/RamaswamyB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/JosephB19,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {Stochastic Approximation Trackers for Model-Based Search},
booktitle = {57th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2019, Monticello, IL, USA, September 24-27, 2019},
pages = {741--748},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ALLERTON.2019.8919816},
doi = {10.1109/ALLERTON.2019.8919816},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/allerton/JosephB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/DiddigiRJB19,
author = {Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Prabuchandran K. J. and
Shalabh Bhatnagar},
editor = {Edith Elkind and
Manuela Veloso and
Noa Agmon and
Matthew E. Taylor},
title = {Actor-Critic Algorithms for Constrained Multi-agent Reinforcement
Learning},
booktitle = {Proceedings of the 18th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} '19, Montreal, QC, Canada, May 13-17,
2019},
pages = {1931--1933},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
year = {2019},
url = {http://dl.acm.org/citation.cfm?id=3331967},
timestamp = {Mon, 18 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/atal/DiddigiRJB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/JosephB19,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {An Adaptive and Incremental Approach to Quantile Estimation},
booktitle = {58th {IEEE} Conference on Decision and Control, {CDC} 2019, Nice,
France, December 11-13, 2019},
pages = {6025--6031},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/CDC40024.2019.9029803},
doi = {10.1109/CDC40024.2019.9029803},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/JosephB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/comad/JohnB19,
author = {Indu John and
Shalabh Bhatnagar},
editor = {Raghu Krishnapuram and
Parag Singla},
title = {Efficient Budget Allocation and Task Assignment in Crowdsourcing},
booktitle = {Proceedings of the {ACM} India Joint International Conference on Data
Science and Management of Data, {COMAD/CODS} 2019, Kolkata, India,
January 3-5, 2019},
pages = {318--321},
publisher = {{ACM}},
year = {2019},
url = {https://doi.org/10.1145/3297001.3297050},
doi = {10.1145/3297001.3297050},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/comad/JohnB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmla/JohnKB19,
author = {Indu John and
Ravikumar Karumanchi and
Shalabh Bhatnagar},
editor = {M. Arif Wani and
Taghi M. Khoshgoftaar and
Dingding Wang and
Huanjing Wang and
Naeem Seliya},
title = {Predictive and Prescriptive Analytics for Performance Optimization:
Framework and a Case Study on a Large-Scale Enterprise System},
booktitle = {18th {IEEE} International Conference On Machine Learning And Applications,
{ICMLA} 2019, Boca Raton, FL, USA, December 16-19, 2019},
pages = {876--881},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICMLA.2019.00152},
doi = {10.1109/ICMLA.2019.00152},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icmla/JohnKB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/SinglaBDBGAK19,
author = {Abhik Singla and
Shounak Bhattacharya and
Dhaivat Dholakiya and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Realizing Learned Quadruped Locomotion Behaviors through Kinematic
Motion Primitives},
booktitle = {International Conference on Robotics and Automation, {ICRA} 2019,
Montreal, QC, Canada, May 20-24, 2019},
pages = {7434--7440},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICRA.2019.8794179},
doi = {10.1109/ICRA.2019.8794179},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icra/SinglaBDBGAK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/BhattacharyaSAD19,
author = {Shounak Bhattacharya and
Abhik Singla and
Abhimanyu and
Dhaivat Dholakiya and
Shalabh Bhatnagar and
Bharadwaj Amrutur and
Ashitava Ghosal and
Shishir Kolathaya},
title = {Learning Active Spine Behaviors for Dynamic and Efficient Locomotion
in Quadruped Robots},
booktitle = {28th {IEEE} International Conference on Robot and Human Interactive
Communication, {RO-MAN} 2019, New Delhi, India, October 14-18, 2019},
pages = {1--6},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/RO-MAN46459.2019.8956332},
doi = {10.1109/RO-MAN46459.2019.8956332},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ro-man/BhattacharyaSAD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/KolathayaGAJSDA19,
author = {Shishir Kolathaya and
Ashitava Ghosal and
Bharadwaj Amrutur and
Ashish Joglekar and
Suhan Shetty and
Dhaivat Dholakiya and
Abhimanyu and
Aditya Sagi and
Shounak Bhattacharya and
Abhik Singla and
Shalabh Bhatnagar},
title = {Trajectory based Deep Policy Search for Quadrupedal Walking},
booktitle = {28th {IEEE} International Conference on Robot and Human Interactive
Communication, {RO-MAN} 2019, New Delhi, India, October 14-18, 2019},
pages = {1--6},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/RO-MAN46459.2019.8956369},
doi = {10.1109/RO-MAN46459.2019.8956369},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ro-man/KolathayaGAJSDA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/saso/JohnSB19,
author = {Indu John and
Aiswarya Sreekantan and
Shalabh Bhatnagar},
title = {Efficient Adaptive Resource Provisioning for Cloud Applications using
Reinforcement Learning},
booktitle = {{IEEE} 4th International Workshops on Foundations and Applications
of Self* Systems, FAS*W@SASO/ICCAC 2019, Umea, Sweden, June 16-20,
2019},
pages = {271--272},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/FAS-W.2019.00077},
doi = {10.1109/FAS-W.2019.00077},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/saso/JohnSB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-00697,
author = {Dhaivat Dholakiya and
Shounak Bhattacharya and
Ajay Gunalan and
Abhik Singla and
Shalabh Bhatnagar and
Bharadwaj Amrutur and
Ashitava Ghosal and
Shishir Kolathaya},
title = {Design, Development and Experimental Realization of a Quadrupedal
Research Platform: Stoch},
journal = {CoRR},
volume = {abs/1901.00697},
year = {2019},
url = {http://arxiv.org/abs/1901.00697},
eprinttype = {arXiv},
eprint = {1901.00697},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-00697.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-03806,
author = {Chandramouli K and
Raghuram Bharadwaj Diddigi and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {An Online Sample Based Method for Mode Estimation using {ODE} Analysis
of Stochastic Approximation Algorithms},
journal = {CoRR},
volume = {abs/1902.03806},
year = {2019},
url = {http://arxiv.org/abs/1902.03806},
eprinttype = {arXiv},
eprint = {1902.03806},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-03806.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1903-03812,
author = {Chandramouli Kamanchi and
Raghuram Bharadwaj Diddigi and
Shalabh Bhatnagar},
title = {Successive Over Relaxation Q-Learning},
journal = {CoRR},
volume = {abs/1903.03812},
year = {2019},
url = {http://arxiv.org/abs/1903.03812},
eprinttype = {arXiv},
eprint = {1903.03812},
timestamp = {Sun, 31 Mar 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1903-03812.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-02907,
author = {Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Actor-Critic Algorithms for Constrained Multi-agent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1905.02907},
year = {2019},
url = {http://arxiv.org/abs/1905.02907},
eprinttype = {arXiv},
eprint = {1905.02907},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-02907.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-03927,
author = {Chandramouli Kamanchi and
Raghuram Bharadwaj Diddigi and
Shalabh Bhatnagar},
title = {Second Order Value Iteration in Reinforcement Learning},
journal = {CoRR},
volume = {abs/1905.03927},
year = {2019},
url = {http://arxiv.org/abs/1905.03927},
eprinttype = {arXiv},
eprint = {1905.03927},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-03927.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-03970,
author = {Sindhu Padakandla and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Reinforcement Learning in Non-Stationary Environments},
journal = {CoRR},
volume = {abs/1905.03970},
year = {2019},
url = {http://arxiv.org/abs/1905.03970},
eprinttype = {arXiv},
eprint = {1905.03970},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-03970.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-06077,
author = {Shounak Bhattacharya and
Abhik Singla and
Abhimanyu and
Dhaivat Dholakiya and
Shalabh Bhatnagar and
Bharadwaj Amrutur and
Ashitava Ghosal and
Shishir Kolathaya},
title = {Learning Active Spine Behaviors for Dynamic and Efficient Locomotion
in Quadruped Robots},
journal = {CoRR},
volume = {abs/1905.06077},
year = {2019},
url = {http://arxiv.org/abs/1905.06077},
eprinttype = {arXiv},
eprint = {1905.06077},
timestamp = {Tue, 28 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-06077.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-06659,
author = {Raghuram Bharadwaj Diddigi and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {Solution of Two-Player Zero-Sum Game by Successive Relaxation},
journal = {CoRR},
volume = {abs/1906.06659},
year = {2019},
url = {http://arxiv.org/abs/1906.06659},
eprinttype = {arXiv},
eprint = {1906.06659},
timestamp = {Mon, 24 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-06659.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-00397,
author = {Indu John and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {Generalized Speedy Q-learning},
journal = {CoRR},
volume = {abs/1911.00397},
year = {2019},
url = {http://arxiv.org/abs/1911.00397},
eprinttype = {arXiv},
eprint = {1911.00397},
timestamp = {Mon, 11 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-00397.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-05697,
author = {Raghuram Bharadwaj Diddigi and
Chandramouli Kamanchi and
Shalabh Bhatnagar},
title = {A Convergent Off-Policy Temporal Difference Algorithm},
journal = {CoRR},
volume = {abs/1911.05697},
year = {2019},
url = {http://arxiv.org/abs/1911.05697},
eprinttype = {arXiv},
eprint = {1911.05697},
timestamp = {Mon, 02 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-05697.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-08826,
author = {Akshay Dharmavaram and
Matthew Riemer and
Shalabh Bhatnagar},
title = {Hierarchical Average Reward Policy Gradient Algorithms},
journal = {CoRR},
volume = {abs/1911.08826},
year = {2019},
url = {http://arxiv.org/abs/1911.08826},
eprinttype = {arXiv},
eprint = {1911.08826},
timestamp = {Tue, 03 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-08826.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-12907,
author = {Sashank Tirumala and
Aditya Sagi and
Kartik Paigwar and
Ashish Joglekar and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Gait Library Synthesis for Quadruped Robots via Augmented Random Search},
journal = {CoRR},
volume = {abs/1912.12907},
year = {2019},
url = {http://arxiv.org/abs/1912.12907},
eprinttype = {arXiv},
eprint = {1912.12907},
timestamp = {Sat, 04 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-12907.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/informs/ZhouB18,
author = {Enlu Zhou and
Shalabh Bhatnagar},
title = {Gradient-Based Adaptive Stochastic Search for Simulation Optimization
Over Continuous Space},
journal = {{INFORMS} J. Comput.},
volume = {30},
number = {1},
pages = {154--167},
year = {2018},
url = {https://doi.org/10.1287/ijoc.2017.0771},
doi = {10.1287/IJOC.2017.0771},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/informs/ZhouB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/JosephB18,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {An incremental off-policy search in a model-free Markov decision process
using a single sample path},
journal = {Mach. Learn.},
volume = {107},
number = {6},
pages = {969--1011},
year = {2018},
url = {https://doi.org/10.1007/s10994-018-5697-1},
doi = {10.1007/S10994-018-5697-1},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/JosephB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/JosephB18a,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {An online prediction algorithm for reinforcement learning with linear
function approximation using cross entropy method},
journal = {Mach. Learn.},
volume = {107},
number = {8-10},
pages = {1385--1429},
year = {2018},
url = {https://doi.org/10.1007/s10994-018-5727-z},
doi = {10.1007/S10994-018-5727-Z},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/JosephB18a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/KarmakarB18,
author = {Prasenjit Karmakar and
Shalabh Bhatnagar},
title = {Two Time-Scale Stochastic Approximation with Controlled Markov Noise
and Off-Policy Temporal-Difference Learning},
journal = {Math. Oper. Res.},
volume = {43},
number = {1},
pages = {130--151},
year = {2018},
url = {https://doi.org/10.1287/moor.2017.0855},
doi = {10.1287/MOOR.2017.0855},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/KarmakarB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/Lakshminarayanan18,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {A Linearly Relaxed Approximate Linear Program for Markov Decision
Processes},
journal = {{IEEE} Trans. Autom. Control.},
volume = {63},
number = {4},
pages = {1185--1191},
year = {2018},
url = {https://doi.org/10.1109/TAC.2017.2743163},
doi = {10.1109/TAC.2017.2743163},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/Lakshminarayanan18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/RamaswamyB18,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Analysis of Gradient Descent Methods With Nondiminishing Bounded Errors},
journal = {{IEEE} Trans. Autom. Control.},
volume = {63},
number = {5},
pages = {1465--1471},
year = {2018},
url = {https://doi.org/10.1109/TAC.2017.2744598},
doi = {10.1109/TAC.2017.2744598},
timestamp = {Wed, 20 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/RamaswamyB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/telsys/BhatnagarPK18,
author = {Shalabh Bhatnagar and
Sanjeev Patel and
Karmeshu},
title = {A stochastic approximation approach to active queue management},
journal = {Telecommun. Syst.},
volume = {68},
number = {1},
pages = {89--104},
year = {2018},
url = {https://doi.org/10.1007/s11235-017-0377-1},
doi = {10.1007/S11235-017-0377-1},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/telsys/BhatnagarPK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/wcl/DiddigiJB18,
author = {Raghuram Bharadwaj Diddigi and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient
Sensor Networks},
journal = {{IEEE} Wirel. Commun. Lett.},
volume = {7},
number = {5},
pages = {712--715},
year = {2018},
url = {https://doi.org/10.1109/LWC.2018.2814576},
doi = {10.1109/LWC.2018.2814576},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/wcl/DiddigiJB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/KJRB18,
author = {Chandramouli K and
Prabuchandran K. J. and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {Generalized Deterministic Perturbations For Stochastic Gradient Search},
booktitle = {57th {IEEE} Conference on Decision and Control, {CDC} 2018, Miami,
FL, USA, December 17-19, 2018},
pages = {5734--5739},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/CDC.2018.8619736},
doi = {10.1109/CDC.2018.8619736},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/KJRB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smartgridcomm/DiddigiRB18,
author = {Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {A unified decision making framework for supply and demand management
in microgrid networks},
booktitle = {2018 {IEEE} International Conference on Communications, Control, and
Computing Technologies for Smart Grids, SmartGridComm 2018, Aalborg,
Denmark, October 29-31, 2018},
pages = {1--7},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SmartGridComm.2018.8587514},
doi = {10.1109/SMARTGRIDCOMM.2018.8587514},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/smartgridcomm/DiddigiRB18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-10287,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {An Incremental Off-policy Search in a Model-free Markov Decision Process
Using a Single Sample Path},
journal = {CoRR},
volume = {abs/1801.10287},
year = {2018},
url = {http://arxiv.org/abs/1801.10287},
eprinttype = {arXiv},
eprint = {1801.10287},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-10287.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-10291,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {A Cross Entropy based Optimization Algorithm with Global Convergence
Guarantees},
journal = {CoRR},
volume = {abs/1801.10291},
year = {2018},
url = {http://arxiv.org/abs/1801.10291},
eprinttype = {arXiv},
eprint = {1801.10291},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-10291.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-06720,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {An Online Prediction Algorithm for Reinforcement Learning with Linear
Function Approximation using Cross Entropy Method},
journal = {CoRR},
volume = {abs/1806.06720},
year = {2018},
url = {http://arxiv.org/abs/1806.06720},
eprinttype = {arXiv},
eprint = {1806.06720},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-06720.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1808-02871,
author = {Prashanth L. A. and
Shalabh Bhatnagar and
Nirav Bhavsar and
Michael C. Fu and
Steven I. Marcus},
title = {Random directions stochastic approximation with deterministic perturbations},
journal = {CoRR},
volume = {abs/1808.02871},
year = {2018},
url = {http://arxiv.org/abs/1808.02871},
eprinttype = {arXiv},
eprint = {1808.02871},
timestamp = {Wed, 20 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1808-02871.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-03842,
author = {Abhik Singla and
Shounak Bhattacharya and
Dhaivat Dholakiya and
Shalabh Bhatnagar and
Ashitava Ghosal and
Bharadwaj Amrutur and
Shishir Kolathaya},
title = {Realizing Learned Quadruped Locomotion Behaviors through Kinematic
Motion Primitives},
journal = {CoRR},
volume = {abs/1810.03842},
year = {2018},
url = {http://arxiv.org/abs/1810.03842},
eprinttype = {arXiv},
eprint = {1810.03842},
timestamp = {Tue, 30 Oct 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-03842.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-03307,
author = {Abhik Singla and
Sindhu Padakandla and
Shalabh Bhatnagar},
title = {Memory-based Deep Reinforcement Learning for Obstacle Avoidance in
{UAV} with Limited Environment Knowledge},
journal = {CoRR},
volume = {abs/1811.03307},
year = {2018},
url = {http://arxiv.org/abs/1811.03307},
eprinttype = {arXiv},
eprint = {1811.03307},
timestamp = {Thu, 22 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-03307.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/Lakshminarayanan17,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {A stability criterion for two timescale stochastic approximation schemes},
journal = {Autom.},
volume = {79},
pages = {108--114},
year = {2017},
url = {https://doi.org/10.1016/j.automatica.2016.12.014},
doi = {10.1016/J.AUTOMATICA.2016.12.014},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/Lakshminarayanan17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/coap/LakshmananB17,
author = {K. Lakshmanan and
Shalabh Bhatnagar},
title = {Quasi-Newton smoothed functional algorithms for unconstrained and
constrained simulation optimization},
journal = {Comput. Optim. Appl.},
volume = {66},
number = {3},
pages = {533--556},
year = {2017},
url = {https://doi.org/10.1007/s10589-016-9875-4},
doi = {10.1007/S10589-016-9875-4},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/coap/LakshmananB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/RamaswamyB17,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {A Generalization of the Borkar-Meyn Theorem for Stochastic Recursive
Inclusions},
journal = {Math. Oper. Res.},
volume = {42},
number = {3},
pages = {648--661},
year = {2017},
url = {https://doi.org/10.1287/moor.2016.0821},
doi = {10.1287/MOOR.2016.0821},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/RamaswamyB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/ABFM17,
author = {Prashanth L. A. and
Shalabh Bhatnagar and
Michael C. Fu and
Steven I. Marcus},
title = {Adaptive System Optimization Using Random Directions Stochastic Approximation},
journal = {{IEEE} Trans. Autom. Control.},
volume = {62},
number = {5},
pages = {2223--2238},
year = {2017},
url = {https://doi.org/10.1109/TAC.2016.2600643},
doi = {10.1109/TAC.2016.2600643},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/ABFM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/telsys/KarmeshuPB17,
author = {Karmeshu and
Sanjeev Patel and
Shalabh Bhatnagar},
title = {Adaptive mean queue size and its rate of change: queue management
with random dropping},
journal = {Telecommun. Syst.},
volume = {65},
number = {2},
pages = {281--295},
year = {2017},
url = {https://doi.org/10.1007/s11235-016-0229-4},
doi = {10.1007/S11235-016-0229-4},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/telsys/KarmeshuPB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/IEEEcloud/KumarPLPGB17,
author = {Sandeep Kumar and
Sindhu Padakandla and
Chandrashekar Lakshminarayanan and
Priyank Parihar and
K. Gopinath and
Shalabh Bhatnagar},
editor = {Geoffrey C. Fox},
title = {Scalable Performance Tuning of Hadoop MapReduce: {A} Noisy Gradient
Approach},
booktitle = {2017 {IEEE} 10th International Conference on Cloud Computing (CLOUD),
Honolulu, HI, USA, June 25-30, 2017},
pages = {375--382},
publisher = {{IEEE} Computer Society},
year = {2017},
url = {https://doi.org/10.1109/CLOUD.2017.55},
doi = {10.1109/CLOUD.2017.55},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/IEEEcloud/KumarPLPGB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/JosephB17,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {A model based search method for prediction in model-free Markov decision
process},
booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017,
Anchorage, AK, USA, May 14-19, 2017},
pages = {170--177},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/IJCNN.2017.7965851},
doi = {10.1109/IJCNN.2017.7965851},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/JosephB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/JosephB17a,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {Bounds for off-policy prediction in reinforcement learning},
booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017,
Anchorage, AK, USA, May 14-19, 2017},
pages = {3991--3997},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/IJCNN.2017.7966359},
doi = {10.1109/IJCNN.2017.7966359},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/JosephB17a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/premi/JosephB17,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
editor = {B. Uma Shankar and
Kuntal Ghosh and
Deba Prasad Mandal and
Shubhra Sankar Ray and
David Zhang and
Sankar K. Pal},
title = {An Incremental Fast Policy Search Using a Single Sample Path},
booktitle = {Pattern Recognition and Machine Intelligence - 7th International Conference,
PReMI 2017, Kolkata, India, December 5-8, 2017, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10597},
pages = {3--10},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-69900-4\_1},
doi = {10.1007/978-3-319-69900-4\_1},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/premi/JosephB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/YajiB17,
author = {Vinayaka G. Yaji and
Shalabh Bhatnagar},
title = {Analysis of stochastic approximation schemes with set-valued maps
in the absence of a stability guarantee and their stabilization},
journal = {CoRR},
volume = {abs/1701.07590},
year = {2017},
url = {http://arxiv.org/abs/1701.07590},
eprinttype = {arXiv},
eprint = {1701.07590},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/YajiB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KRB17,
author = {Chandramouli K and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {Deterministic Perturbations For Simultaneous Perturbation Methods
Using Circulant Matrices},
journal = {CoRR},
volume = {abs/1702.06250},
year = {2017},
url = {http://arxiv.org/abs/1702.06250},
eprinttype = {arXiv},
eprint = {1702.06250},
timestamp = {Mon, 18 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/KRB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Lakshminarayanan17,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {A Linearly Relaxed Approximate Linear Program for Markov Decision
Processes},
journal = {CoRR},
volume = {abs/1704.02544},
year = {2017},
url = {http://arxiv.org/abs/1704.02544},
eprinttype = {arXiv},
eprint = {1704.02544},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Lakshminarayanan17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-07732,
author = {Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Shalabh Bhatnagar},
title = {Multi-Agent Q-Learning for Minimizing Demand-Supply Power Deficit
in Microgrids},
journal = {CoRR},
volume = {abs/1708.07732},
year = {2017},
url = {http://arxiv.org/abs/1708.07732},
eprinttype = {arXiv},
eprint = {1708.07732},
timestamp = {Mon, 18 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-07732.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-08113,
author = {Raghuram Bharadwaj Diddigi and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Novel Sensor Scheduling Scheme for Intruder Tracking in Energy Efficient
Sensor Networks},
journal = {CoRR},
volume = {abs/1708.08113},
year = {2017},
url = {http://arxiv.org/abs/1708.08113},
eprinttype = {arXiv},
eprint = {1708.08113},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-08113.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1709-04673,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Conditions for Stability and Convergence of Set-Valued Stochastic
Approximations: Applications to Approximate Value and Fixed point
Iterations with Noise},
journal = {CoRR},
volume = {abs/1709.04673},
year = {2017},
url = {http://arxiv.org/abs/1709.04673},
eprinttype = {arXiv},
eprint = {1709.04673},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1709-04673.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-05078,
author = {Raghuram Bharadwaj Diddigi and
Sai Koti Reddy Danda and
Krishnasuri Narayanam and
Shalabh Bhatnagar},
title = {A unified decision making framework for supply and demand management
in microgrid networks},
journal = {CoRR},
volume = {abs/1711.05078},
year = {2017},
url = {http://arxiv.org/abs/1711.05078},
eprinttype = {arXiv},
eprint = {1711.05078},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-05078.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-04303,
author = {Jayvant Anantpur and
Nagendra Dwarakanath Gulur and
Shivaram Kalyanakrishnan and
Shalabh Bhatnagar and
R. Govindarajan},
title = {{RLWS:} {A} Reinforcement Learning based {GPU} Warp Scheduler},
journal = {CoRR},
volume = {abs/1712.04303},
year = {2017},
url = {http://arxiv.org/abs/1712.04303},
eprinttype = {arXiv},
eprint = {1712.04303},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-04303.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/deds/BhatnagarL16,
author = {Shalabh Bhatnagar and
K. Lakshmanan},
title = {Multiscale Q-learning with linear function approximation},
journal = {Discret. Event Dyn. Syst.},
volume = {26},
number = {3},
pages = {477--509},
year = {2016},
url = {https://doi.org/10.1007/s10626-015-0216-z},
doi = {10.1007/S10626-015-0216-Z},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/deds/BhatnagarL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scl/APBC16,
author = {Prashanth L. A. and
H. L. Prasad and
Shalabh Bhatnagar and
Prakash Chandra},
title = {A constrained optimization perspective on actor-critic algorithms
and application to network routing},
journal = {Syst. Control. Lett.},
volume = {92},
pages = {46--51},
year = {2016},
url = {https://doi.org/10.1016/j.sysconle.2016.02.020},
doi = {10.1016/J.SYSCONLE.2016.02.020},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scl/APBC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/JBB16,
author = {Prabuchandran K. J. and
Shalabh Bhatnagar and
Vivek S. Borkar},
title = {Actor-Critic Algorithms with Online Feature Adaptation},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {26},
number = {4},
pages = {24:1--24:26},
year = {2016},
url = {https://doi.org/10.1145/2868723},
doi = {10.1145/2868723},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/JBB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/ReddyAB16,
author = {Sai Koti Reddy Danda and
Prashanth L. A. and
Shalabh Bhatnagar},
title = {Improved Hessian estimation for adaptive random directions stochastic
approximation},
booktitle = {55th {IEEE} Conference on Decision and Control, {CDC} 2016, Las Vegas,
NV, USA, December 12-14, 2016},
pages = {3682--3687},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/CDC.2016.7798823},
doi = {10.1109/CDC.2016.7798823},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/ReddyAB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/JosephB16,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
editor = {Gal A. Kaminka and
Maria Fox and
Paolo Bouquet and
Eyke H{\"{u}}llermeier and
Virginia Dignum and
Frank Dignum and
Frank van Harmelen},
title = {Revisiting the Cross Entropy Method with Applications in Stochastic
Global Optimization and Reinforcement Learning},
booktitle = {{ECAI} 2016 - 22nd European Conference on Artificial Intelligence,
29 August-2 September 2016, The Hague, The Netherlands - Including
Prestigious Applications of Artificial Intelligence {(PAIS} 2016)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {285},
pages = {1026--1034},
publisher = {{IOS} Press},
year = {2016},
url = {https://doi.org/10.3233/978-1-61499-672-9-1026},
doi = {10.3233/978-1-61499-672-9-1026},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecai/JosephB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecai/MaityLPB16,
author = {Raj Kumar Maity and
Chandrashekar Lakshminarayanan and
Sindhu Padakandla and
Shalabh Bhatnagar},
editor = {Gal A. Kaminka and
Maria Fox and
Paolo Bouquet and
Eyke H{\"{u}}llermeier and
Virginia Dignum and
Frank Dignum and
Frank van Harmelen},
title = {Shaping Proto-Value Functions Using Rewards},
booktitle = {{ECAI} 2016 - 22nd European Conference on Artificial Intelligence,
29 August-2 September 2016, The Hague, The Netherlands - Including
Prestigious Applications of Artificial Intelligence {(PAIS} 2016)},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {285},
pages = {1690--1691},
publisher = {{IOS} Press},
year = {2016},
url = {https://doi.org/10.3233/978-1-61499-672-9-1690},
doi = {10.3233/978-1-61499-672-9-1690},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecai/MaityLPB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/NB16,
author = {Ranganath B. N. and
Shalabh Bhatnagar},
title = {Scalable focussed entity resolution},
booktitle = {2016 International Joint Conference on Neural Networks, {IJCNN} 2016,
Vancouver, BC, Canada, July 24-29, 2016},
pages = {3570--3577},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/IJCNN.2016.7727658},
doi = {10.1109/IJCNN.2016.7727658},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/NB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wsc/JosephB16,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {A randomized algorithm for continuous optimization},
booktitle = {Winter Simulation Conference, {WSC} 2016, Washington, DC, USA, December
11-14, 2016},
pages = {907--918},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/WSC.2016.7822152},
doi = {10.1109/WSC.2016.7822152},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/wsc/JosephB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KarmeshuPB16,
author = {Karmeshu and
Sanjeev Patel and
Shalabh Bhatnagar},
title = {Adaptive Mean Queue Size and Its Rate of Change: Queue Management
with Random Dropping},
journal = {CoRR},
volume = {abs/1602.02241},
year = {2016},
url = {http://arxiv.org/abs/1602.02241},
eprinttype = {arXiv},
eprint = {1602.02241},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KarmeshuPB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RamaswamyB16,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Gradient-based learning algorithms with constant-error estimators:
stability and convergence},
journal = {CoRR},
volume = {abs/1604.00151},
year = {2016},
url = {http://arxiv.org/abs/1604.00151},
eprinttype = {arXiv},
eprint = {1604.00151},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RamaswamyB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KarmakarMB16,
author = {Prasenjit Karmakar and
Raj Kumar Maity and
Shalabh Bhatnagar},
title = {On a convergent off -policy temporal difference learning algorithm
in on-line learning environment},
journal = {CoRR},
volume = {abs/1605.06076},
year = {2016},
url = {http://arxiv.org/abs/1605.06076},
eprinttype = {arXiv},
eprint = {1605.06076},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KarmakarMB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/YajiB16,
author = {Vinayaka Yaji and
Shalabh Bhatnagar},
title = {Stochastic Recursive Inclusions with Non-Additive Iterate-Dependent
Markov Noise},
journal = {CoRR},
volume = {abs/1607.04735},
year = {2016},
url = {http://arxiv.org/abs/1607.04735},
eprinttype = {arXiv},
eprint = {1607.04735},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/YajiB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/JosephB16,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
title = {A Cross Entropy based Stochastic Approximation Algorithm for Reinforcement
Learning with Linear Function Approximation},
journal = {CoRR},
volume = {abs/1609.09449},
year = {2016},
url = {http://arxiv.org/abs/1609.09449},
eprinttype = {arXiv},
eprint = {1609.09449},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/JosephB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/YajiB16a,
author = {Vinayaka Yaji and
Shalabh Bhatnagar},
title = {Stochastic Recursive Inclusions in two timescales with non-additive
iterate dependent Markov noise},
journal = {CoRR},
volume = {abs/1611.05961},
year = {2016},
url = {http://arxiv.org/abs/1611.05961},
eprinttype = {arXiv},
eprint = {1611.05961},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/YajiB16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KumarPLPGB16,
author = {Sandeep Kumar and
Sindhu Padakandla and
Chandrashekar Lakshminarayanan and
Priyank Parihar and
K. Gopinath and
Shalabh Bhatnagar},
title = {Performance Tuning of Hadoop MapReduce: {A} Noisy Gradient Approach},
journal = {CoRR},
volume = {abs/1611.10052},
year = {2016},
url = {http://arxiv.org/abs/1611.10052},
eprinttype = {arXiv},
eprint = {1611.10052},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KumarPLPGB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KarmakarB16,
author = {Prasenjit Karmakar and
Shalabh Bhatnagar},
title = {A note on the function approximation error bound for risk-sensitive
reinforcement learning},
journal = {CoRR},
volume = {abs/1612.07562},
year = {2016},
url = {http://arxiv.org/abs/1612.07562},
eprinttype = {arXiv},
eprint = {1612.07562},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KarmakarB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jota/BhatnagarA15,
author = {Shalabh Bhatnagar and
Prashanth L. A.},
title = {Simultaneous Perturbation Newton Algorithms for Simulation Optimization},
journal = {J. Optim. Theory Appl.},
volume = {164},
number = {2},
pages = {621--643},
year = {2015},
url = {https://doi.org/10.1007/s10957-013-0507-1},
doi = {10.1007/S10957-013-0507-1},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jota/BhatnagarA15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scl/YajiB15,
author = {Vinayaka Yaji and
Shalabh Bhatnagar},
title = {Necessary and sufficient conditions for optimality in constrained
general sum stochastic games},
journal = {Syst. Control. Lett.},
volume = {85},
pages = {8--15},
year = {2015},
url = {https://doi.org/10.1016/j.sysconle.2015.08.003},
doi = {10.1016/J.SYSCONLE.2015.08.003},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scl/YajiB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simulation/APDBD15,
author = {Prashanth L. A. and
H. L. Prasad and
Nirmit Desai and
Shalabh Bhatnagar and
Gargi Dasgupta},
title = {Simultaneous perturbation methods for adaptive labor staffing in service
systems},
journal = {Simul.},
volume = {91},
number = {5},
pages = {432--455},
year = {2015},
url = {https://doi.org/10.1177/0037549715581198},
doi = {10.1177/0037549715581198},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simulation/APDBD15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcom/PadakandlaJB15,
author = {Sindhu Padakandla and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Energy Sharing for Multiple Sensor Nodes With Finite Buffers},
journal = {{IEEE} Trans. Commun.},
volume = {63},
number = {5},
pages = {1811--1823},
year = {2015},
url = {https://doi.org/10.1109/TCOMM.2015.2415777},
doi = {10.1109/TCOMM.2015.2415777},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcom/PadakandlaJB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/Lakshminarayanan15,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
editor = {Blai Bonet and
Sven Koenig},
title = {A Generalized Reduced Linear Program for Markov Decision Processes},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {2722--2728},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9620},
doi = {10.1609/AAAI.V29I1.9620},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/Lakshminarayanan15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/PrasadAB15,
author = {H. L. Prasad and
Prashanth L. A. and
Shalabh Bhatnagar},
editor = {Gerhard Weiss and
Pinar Yolum and
Rafael H. Bordini and
Edith Elkind},
title = {Two-Timescale Algorithms for Learning Nash Equilibria in General-Sum
Stochastic Games},
booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015},
pages = {1371--1379},
publisher = {{ACM}},
year = {2015},
url = {http://dl.acm.org/citation.cfm?id=2773328},
timestamp = {Tue, 08 Mar 2022 10:12:47 +0100},
biburl = {https://dblp.org/rec/conf/atal/PrasadAB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/comsnets/JNB15,
author = {Prabuchandran K. J. and
Hemanth Kumar A. N and
Shalabh Bhatnagar},
title = {Decentralized learning for traffic signal control},
booktitle = {7th International Conference on Communication Systems and Networks,
{COMSNETS} 2015, Bangalore, India, January 6-10, 2015},
pages = {1--6},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/COMSNETS.2015.7098712},
doi = {10.1109/COMSNETS.2015.7098712},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/comsnets/JNB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/JosephB15,
author = {Ajin George Joseph and
Shalabh Bhatnagar},
editor = {Sabri Arik and
Tingwen Huang and
Weng Kin Lai and
Qingshan Liu},
title = {A Stochastic Approximation Algorithm for Quantile Estimation},
booktitle = {Neural Information Processing - 22nd International Conference, {ICONIP}
2015, Istanbul, Turkey, November 9-12, 2015, Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {9490},
pages = {311--319},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-26535-3\_36},
doi = {10.1007/978-3-319-26535-3\_36},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iconip/JosephB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RamaswamyB15,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {A Generalization of the Borkar-Meyn Theorem for Stochastic Recursive
Inclusions},
journal = {CoRR},
volume = {abs/1502.01953},
year = {2015},
url = {http://arxiv.org/abs/1502.01953},
eprinttype = {arXiv},
eprint = {1502.01953},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RamaswamyB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RamaswamyB15a,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Stochastic recursive inclusions with two timescales},
journal = {CoRR},
volume = {abs/1502.01956},
year = {2015},
url = {http://arxiv.org/abs/1502.01956},
eprinttype = {arXiv},
eprint = {1502.01956},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RamaswamyB15a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AB15,
author = {Prashanth L. A. and
Shalabh Bhatnagar},
title = {Adaptive system optimization using (simultaneous) random directions
stochastic approximation},
journal = {CoRR},
volume = {abs/1502.05577},
year = {2015},
url = {http://arxiv.org/abs/1502.05577},
eprinttype = {arXiv},
eprint = {1502.05577},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PadakandlaJB15,
author = {Sindhu Padakandla and
Prabuchandran K. J. and
Shalabh Bhatnagar},
title = {Energy Sharing for Multiple Sensor Nodes with Finite Buffers},
journal = {CoRR},
volume = {abs/1503.04964},
year = {2015},
url = {http://arxiv.org/abs/1503.04964},
eprinttype = {arXiv},
eprint = {1503.04964},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PadakandlaJB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KarmakarB15,
author = {Prasenjit Karmakar and
Shalabh Bhatnagar},
title = {Two Timescale Stochastic Approximation with Controlled Markov noise},
journal = {CoRR},
volume = {abs/1503.09105},
year = {2015},
url = {http://arxiv.org/abs/1503.09105},
eprinttype = {arXiv},
eprint = {1503.09105},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KarmakarB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RamaswamyB15b,
author = {Arunselvan Ramaswamy and
Shalabh Bhatnagar},
title = {Stability of Stochastic Approximations with 'Controlled Markov' Noise
and Temporal Difference Learning},
journal = {CoRR},
volume = {abs/1504.06043},
year = {2015},
url = {http://arxiv.org/abs/1504.06043},
eprinttype = {arXiv},
eprint = {1504.06043},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RamaswamyB15b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/YajiB15,
author = {Vinayaka Yaji and
Shalabh Bhatnagar},
title = {A bi-convex optimization problem to compute Nash equilibrium in n-player
games and an algorithm},
journal = {CoRR},
volume = {abs/1504.06828},
year = {2015},
url = {http://arxiv.org/abs/1504.06828},
eprinttype = {arXiv},
eprint = {1504.06828},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/YajiB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PrasadB15,
author = {H. L. Prasad and
Shalabh Bhatnagar},
title = {A Study of Gradient Descent Schemes for General-Sum Stochastic Games},
journal = {CoRR},
volume = {abs/1507.00093},
year = {2015},
url = {http://arxiv.org/abs/1507.00093},
eprinttype = {arXiv},
eprint = {1507.00093},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PrasadB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/APBC15,
author = {Prashanth L. A. and
H. L. Prasad and
Shalabh Bhatnagar and
Prakash Chandra},
title = {A constrained optimization perspective on actor critic algorithms
and application to network routing},
journal = {CoRR},
volume = {abs/1507.07984},
year = {2015},
url = {http://arxiv.org/abs/1507.07984},
eprinttype = {arXiv},
eprint = {1507.07984},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/APBC15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/NarayananMB15,
author = {Chandrashekar Lakshmi Narayanan and
Raj Kumar Maity and
Shalabh Bhatnagar},
title = {Shaping Proto-Value Functions via Rewards},
journal = {CoRR},
volume = {abs/1511.08589},
year = {2015},
url = {http://arxiv.org/abs/1511.08589},
eprinttype = {arXiv},
eprint = {1511.08589},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/NarayananMB15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/GhoshdastidarDB14,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {Newton-based stochastic optimization using q-Gaussian smoothed functional
algorithms},
journal = {Autom.},
volume = {50},
number = {10},
pages = {2606--2614},
year = {2014},
url = {https://doi.org/10.1016/j.automatica.2014.08.021},
doi = {10.1016/J.AUTOMATICA.2014.08.021},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/GhoshdastidarDB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/itor/ChakravartyPB14,
author = {Saswata Chakravarty and
Sindhu Padakandla and
Shalabh Bhatnagar},
title = {A simulation-based algorithm for optimal pricing policy under demand
uncertainty},
journal = {Int. Trans. Oper. Res.},
volume = {21},
number = {5},
pages = {737--760},
year = {2014},
url = {https://doi.org/10.1111/itor.12064},
doi = {10.1111/ITOR.12064},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/itor/ChakravartyPB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/GhoshdastidarDB14,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {Smoothed Functional Algorithms for Stochastic Optimization Using \emph{q}-Gaussian
Distributions},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {24},
number = {3},
pages = {17:1--17:26},
year = {2014},
url = {https://doi.org/10.1145/2628434},
doi = {10.1145/2628434},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/GhoshdastidarDB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/winet/ACB14,
author = {Prashanth L. A. and
Abhranil Chatterjee and
Shalabh Bhatnagar},
title = {Two timescale convergent Q-learning for sleep-scheduling in wireless
sensor networks},
journal = {Wirel. Networks},
volume = {20},
number = {8},
pages = {2589--2604},
year = {2014},
url = {https://doi.org/10.1007/s11276-014-0762-6},
doi = {10.1007/S11276-014-0762-6},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/winet/ACB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/LakshminarayananB14,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {Approximate Dynamic Programming with (min; +) linear function approximation
for Markov decision processes},
booktitle = {53rd {IEEE} Conference on Decision and Control, {CDC} 2014, Los Angeles,
CA, USA, December 15-17, 2014},
pages = {1588--1593},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/CDC.2014.7039626},
doi = {10.1109/CDC.2014.7039626},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/LakshminarayananB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/JBB14,
author = {Prabuchandran K. J. and
Shalabh Bhatnagar and
Vivek S. Borkar},
title = {An actor critic algorithm based on Grassmanian search},
booktitle = {53rd {IEEE} Conference on Decision and Control, {CDC} 2014, Los Angeles,
CA, USA, December 15-17, 2014},
pages = {3597--3602},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/CDC.2014.7039948},
doi = {10.1109/CDC.2014.7039948},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/JBB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/comsnets/ACB14,
author = {Prashanth L. A. and
Abhranil Chatterjee and
Shalabh Bhatnagar},
title = {Adaptive sleep-wake control using reinforcement learning in sensor
networks},
booktitle = {Sixth International Conference on Communication Systems and Networks,
{COMSNETS} 2014, Bangalore, India, January 6-10, 2014},
pages = {1--8},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/COMSNETS.2014.6734874},
doi = {10.1109/COMSNETS.2014.6734874},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/comsnets/ACB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hcomp/LakshminarayananDBB14,
author = {Chandrashekar Lakshminarayanan and
Ayush Dubey and
Shalabh Bhatnagar and
Chithralekha Balamurugan},
editor = {Jeffrey P. Bigham and
David C. Parkes},
title = {A Markov Decision Process Framework for Predictable Job Completion
Times on Crowdsourcing Platforms},
booktitle = {Proceedings of the Seconf {AAAI} Conference on Human Computation and
Crowdsourcing, {HCOMP} 2014, November 2-4, 2014, Pittsburgh, Pennsylvania,
{USA}},
pages = {34--35},
publisher = {{AAAI}},
year = {2014},
url = {https://doi.org/10.1609/hcomp.v2i1.13183},
doi = {10.1609/HCOMP.V2I1.13183},
timestamp = {Tue, 05 Sep 2023 11:10:11 +0200},
biburl = {https://dblp.org/rec/conf/hcomp/LakshminarayananDBB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/itsc/JNB14,
author = {Prabuchandran K. J. and
Hemanth Kumar A. N and
Shalabh Bhatnagar},
title = {Multi-agent reinforcement learning for traffic signal control},
booktitle = {17th International {IEEE} Conference on Intelligent Transportation
Systems, {ITSC} 2014, Qingdao, China, October 8-11, 2014},
pages = {2529--2534},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ITSC.2014.6958095},
doi = {10.1109/ITSC.2014.6958095},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/itsc/JNB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YaoSSMB14,
author = {Hengshuai Yao and
Csaba Szepesv{\'{a}}ri and
Richard S. Sutton and
Joseph Modayil and
Shalabh Bhatnagar},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Universal Option Models},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {990--998},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/996a7fa078cc36c46d02f9af3bef918b-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/YaoSSMB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wsc/ZhouBC14,
author = {Enlu Zhou and
Shalabh Bhatnagar and
Xi Chen},
editor = {Stephen J. Buckley and
John A. Miller},
title = {Simulation optimization via gradient-based stochastic search},
booktitle = {Proceedings of the 2014 Winter Simulation Conference, Savannah, GA,
USA, December 7-10, 2014},
pages = {3869--3879},
publisher = {{IEEE/ACM}},
year = {2014},
url = {https://doi.org/10.1109/WSC.2014.7020213},
doi = {10.1109/WSC.2014.7020213},
timestamp = {Thu, 11 Apr 2024 20:25:47 +0200},
biburl = {https://dblp.org/rec/conf/wsc/ZhouBC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PrasadAB14,
author = {H. L. Prasad and
Prashanth L. A. and
Shalabh Bhatnagar},
title = {Algorithms for Nash Equilibria in General-Sum Stochastic Games},
journal = {CoRR},
volume = {abs/1401.2086},
year = {2014},
url = {http://arxiv.org/abs/1401.2086},
eprinttype = {arXiv},
eprint = {1401.2086},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PrasadAB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LakshminarayananB14,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {Approximate Dynamic Programming based on Projection onto the (min,
+) subsemimodule},
journal = {CoRR},
volume = {abs/1403.4175},
year = {2014},
url = {http://arxiv.org/abs/1403.4175},
eprinttype = {arXiv},
eprint = {1403.4175},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LakshminarayananB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LakshminarayananB14a,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {Approximate dynamic programming with {\textdollar}({\textbackslash}min,
+){\textdollar} linear function approximation for Markov decision
processes},
journal = {CoRR},
volume = {abs/1403.4179},
year = {2014},
url = {http://arxiv.org/abs/1403.4179},
eprinttype = {arXiv},
eprint = {1403.4179},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LakshminarayananB14a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LakshminarayananB14b,
author = {Chandrashekar Lakshminarayanan and
Shalabh Bhatnagar},
title = {A Generalized Reduced Linear Program for Markov Decision Processes},
journal = {CoRR},
volume = {abs/1409.3536},
year = {2014},
url = {http://arxiv.org/abs/1409.3536},
eprinttype = {arXiv},
eprint = {1409.3536},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LakshminarayananB14b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jstsp/BhatnagarBJ13,
author = {Shalabh Bhatnagar and
Vivek S. Borkar and
Prabuchandran K. J.},
title = {Feature Search in the Grassmanian in Online Reinforcement Learning},
journal = {{IEEE} J. Sel. Top. Signal Process.},
volume = {7},
number = {5},
pages = {746--758},
year = {2013},
url = {https://doi.org/10.1109/JSTSP.2013.2255022},
doi = {10.1109/JSTSP.2013.2255022},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jstsp/BhatnagarBJ13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/wcl/JMB13,
author = {Prabuchandran K. J. and
Sunil Kumar Meena and
Shalabh Bhatnagar},
title = {Q-Learning Based Energy Management Policies for a Single Sensor Node
with Finite Buffer},
journal = {{IEEE} Wirel. Commun. Lett.},
volume = {2},
number = {1},
pages = {82--85},
year = {2013},
url = {https://doi.org/10.1109/WCL.2012.112012.120754},
doi = {10.1109/WCL.2012.112012.120754},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/wcl/JMB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/AnanthapadmanabharaoPDB13,
author = {Prashanth Lakshmanrao Ananthapadmanabharao and
Horabailu Laxminarayana Prasad and
Nirmit Desai and
Shalabh Bhatnagar},
editor = {Maria L. Gini and
Onn Shehory and
Takayuki Ito and
Catholijn M. Jonker},
title = {Mechanisms for hostile agents with capacity constraints},
booktitle = {International conference on Autonomous Agents and Multi-Agent Systems,
{AAMAS} '13, Saint Paul, MN, USA, May 6-10, 2013},
pages = {659--666},
publisher = {{IFAAMAS}},
year = {2013},
url = {http://dl.acm.org/citation.cfm?id=2485024},
timestamp = {Thu, 09 Sep 2021 16:09:54 +0200},
biburl = {https://dblp.org/rec/conf/atal/AnanthapadmanabharaoPDB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GhoshdastidarDB13,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {Newton based Stochastic Optimization using q-Gaussian Smoothed Functional
Algorithms},
journal = {CoRR},
volume = {abs/1311.2296},
year = {2013},
url = {http://arxiv.org/abs/1311.2296},
eprinttype = {arXiv},
eprint = {1311.2296},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GhoshdastidarDB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AnanthapadmanabharaoCB13,
author = {Prashanth Lakshmanrao Ananthapadmanabharao and
Abhranil Chatterjee and
Shalabh Bhatnagar},
title = {Reinforcement Learning for Sleep-Wake Scheduling in Sensor Networks},
journal = {CoRR},
volume = {abs/1312.7292},
year = {2013},
url = {http://arxiv.org/abs/1312.7292},
eprinttype = {arXiv},
eprint = {1312.7292},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AnanthapadmanabharaoCB13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PrashanthPDBD13,
author = {Prashanth L. A. and
H. L. Prasad and
Nirmit Desai and
Shalabh Bhatnagar and
Gargi Dasgupta},
title = {Simultaneous Perturbation Methods for Adaptive Labor Staffing in Service
Systems},
journal = {CoRR},
volume = {abs/1312.7430},
year = {2013},
url = {http://arxiv.org/abs/1312.7430},
eprinttype = {arXiv},
eprint = {1312.7430},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PrashanthPDBD13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/PrasadB12,
author = {H. L. Prasad and
Shalabh Bhatnagar},
title = {General-sum stochastic games: Verifiability conditions for Nash equilibria},
journal = {Autom.},
volume = {48},
number = {11},
pages = {2923--2930},
year = {2012},
url = {https://doi.org/10.1016/j.automatica.2012.06.088},
doi = {10.1016/J.AUTOMATICA.2012.06.088},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/PrasadB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cn/VemuBH12,
author = {Koteswara Rao Vemu and
Shalabh Bhatnagar and
N. Hemachandra},
title = {Optimal multi-layered congestion based pricing schemes for enhanced
QoS},
journal = {Comput. Networks},
volume = {56},
number = {4},
pages = {1249--1262},
year = {2012},
url = {https://doi.org/10.1016/j.comnet.2011.12.004},
doi = {10.1016/J.COMNET.2011.12.004},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cn/VemuBH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jota/BhatnagarL12,
author = {Shalabh Bhatnagar and
K. Lakshmanan},
title = {An Online Actor-Critic Algorithm with Function Approximation for Constrained
Markov Decision Processes},
journal = {J. Optim. Theory Appl.},
volume = {153},
number = {3},
pages = {688--708},
year = {2012},
url = {https://doi.org/10.1007/s10957-012-9989-5},
doi = {10.1007/S10957-012-9989-5},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jota/BhatnagarL12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tvt/PrashanthB12,
author = {Prashanth L. A. and
Shalabh Bhatnagar},
title = {Threshold Tuning Using Stochastic Optimization for Graded Signal Control},
journal = {{IEEE} Trans. Veh. Technol.},
volume = {61},
number = {9},
pages = {3865--3880},
year = {2012},
url = {https://doi.org/10.1109/TVT.2012.2209904},
doi = {10.1109/TVT.2012.2209904},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tvt/PrashanthB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/LakshmananB12,
author = {K. Lakshmanan and
Shalabh Bhatnagar},
title = {A novel Q-learning algorithm with function approximation for constrained
Markov decision processes},
booktitle = {50th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2012, Allerton Park {\&} Retreat Center, Monticello,
IL, USA, October 1-5, 2012},
pages = {400--405},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/Allerton.2012.6483246},
doi = {10.1109/ALLERTON.2012.6483246},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/allerton/LakshmananB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isit/GhoshdastidarDB12,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {q-Gaussian based Smoothed Functional algorithms for stochastic optimization},
booktitle = {Proceedings of the 2012 {IEEE} International Symposium on Information
Theory, {ISIT} 2012, Cambridge, MA, USA, July 1-6, 2012},
pages = {1059--1063},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ISIT.2012.6283013},
doi = {10.1109/ISIT.2012.6283013},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isit/GhoshdastidarDB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1202-5665,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {q-Gaussian based Smoothed Functional Algorithm for Stochastic Optimization},
journal = {CoRR},
volume = {abs/1202.5665},
year = {2012},
url = {http://arxiv.org/abs/1202.5665},
eprinttype = {arXiv},
eprint = {1202.5665},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1202-5665.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-4832,
author = {Debarghya Ghoshdastidar and
Ambedkar Dukkipati and
Shalabh Bhatnagar},
title = {Smoothed Functional Algorithms for Stochastic Optimization using q-Gaussian
Distributions},
journal = {CoRR},
volume = {abs/1206.4832},
year = {2012},
url = {http://arxiv.org/abs/1206.4832},
eprinttype = {arXiv},
eprint = {1206.4832},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-4832.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scl/Bhatnagar11,
author = {Shalabh Bhatnagar},
title = {The Borkar-Meyn theorem for asynchronous stochastic approximations},
journal = {Syst. Control. Lett.},
volume = {60},
number = {7},
pages = {472--478},
year = {2011},
url = {https://doi.org/10.1016/j.sysconle.2011.04.002},
doi = {10.1016/J.SYSCONLE.2011.04.002},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scl/Bhatnagar11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tase/BhatnagarMH11,
author = {Shalabh Bhatnagar and
Vivek Kumar Mishra and
N. Hemachandra},
title = {Stochastic Algorithms for Discrete Parameter Simulation Optimization},
journal = {{IEEE} Trans Autom. Sci. Eng.},
volume = {8},
number = {4},
pages = {780--793},
year = {2011},
url = {https://doi.org/10.1109/TASE.2011.2159375},
doi = {10.1109/TASE.2011.2159375},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tase/BhatnagarMH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcom/KarmeshuBM11,
author = {Karmeshu and
Shalabh Bhatnagar and
Vivek Kumar Mishra},
title = {An Optimized {SDE} Model for Slotted Aloha},
journal = {{IEEE} Trans. Commun.},
volume = {59},
number = {6},
pages = {1502--1508},
year = {2011},
url = {https://doi.org/10.1109/TCOMM.2011.041111.090113},
doi = {10.1109/TCOMM.2011.041111.090113},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcom/KarmeshuBM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tits/PrashanthB11,
author = {Prashanth L. A. and
Shalabh Bhatnagar},
title = {Reinforcement Learning With Function Approximation for Traffic Signal
Control},
journal = {{IEEE} Trans. Intell. Transp. Syst.},
volume = {12},
number = {2},
pages = {412--421},
year = {2011},
url = {https://doi.org/10.1109/TITS.2010.2091408},
doi = {10.1109/TITS.2010.2091408},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tits/PrashanthB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/BhatnagarHM11,
author = {Shalabh Bhatnagar and
N. Hemachandra and
Vivek Kumar Mishra},
title = {Stochastic approximation algorithms for constrained optimization via
simulation},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {21},
number = {3},
pages = {15:1--15:22},
year = {2011},
url = {https://doi.org/10.1145/1921598.1921599},
doi = {10.1145/1921598.1921599},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/BhatnagarHM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdcit/LakshmananB11,
author = {K. Lakshmanan and
Shalabh Bhatnagar},
editor = {Raja Natarajan and
Adegboyega K. Ojo},
title = {Smoothed Functional and Quasi-Newton Algorithms for Routing in Multi-stage
Queueing Network with Constraints},
booktitle = {Distributed Computing and Internet Technology - 7th International
Conference, {ICDCIT} 2011, Bhubaneshwar, India, February 9-12, 2011.
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6536},
pages = {175--186},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-19056-8\_12},
doi = {10.1007/978-3-642-19056-8\_12},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdcit/LakshmananB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icsoc/PrashanthPDBD11,
author = {Prashanth L. A. and
H. L. Prasad and
Nirmit Desai and
Shalabh Bhatnagar and
Gargi Banerjee Dasgupta},
editor = {Gerti Kappel and
Zakaria Maamar and
Hamid R. Motahari Nezhad},
title = {Stochastic Optimization for Adaptive Labor Staffing in Service Systems},
booktitle = {Service-Oriented Computing - 9th International Conference, {ICSOC}
2011, Paphos, Cyprus, December 5-8, 2011 Proceedings},
series = {Lecture Notes in Computer Science},
volume = {7084},
pages = {487--494},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-25535-9\_33},
doi = {10.1007/978-3-642-25535-9\_33},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icsoc/PrashanthPDBD11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/itsc/AB11,
author = {Prashanth L. A. and
Shalabh Bhatnagar},
title = {Reinforcement learning with average cost for adaptive control of traffic
lights at intersections},
booktitle = {14th International {IEEE} Conference on Intelligent Transportation
Systems, {ITSC} 2011, Washington, DC, USA, October 5-7, 2011},
pages = {1640--1645},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ITSC.2011.6082823},
doi = {10.1109/ITSC.2011.6082823},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/itsc/AB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/scl/Bhatnagar10,
author = {Shalabh Bhatnagar},
title = {An actor-critic algorithm with function approximation for discounted
cost constrained Markov decision processes},
journal = {Syst. Control. Lett.},
volume = {59},
number = {12},
pages = {760--766},
year = {2010},
url = {https://doi.org/10.1016/j.sysconle.2010.08.013},
doi = {10.1016/J.SYSCONLE.2010.08.013},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/scl/Bhatnagar10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simulation/ChakrabortyB10,
author = {Anshuk Chakraborty and
Shalabh Bhatnagar},
title = {Optimized Policies for the Retransmission Probabilities in Slotted
Aloha},
journal = {Simul.},
volume = {86},
number = {4},
pages = {247--261},
year = {2010},
url = {https://doi.org/10.1177/0037549709349324},
doi = {10.1177/0037549709349324},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simulation/ChakrabortyB10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/winet/ReddyBRC10,
author = {G. Ramana Reddy and
Shalabh Bhatnagar and
V. Rakesh and
Vijay Prakash Chaturvedi},
title = {An efficient algorithm for scheduling in bluetooth piconets and scatternets},
journal = {Wirel. Networks},
volume = {16},
number = {7},
pages = {1799--1816},
year = {2010},
url = {https://doi.org/10.1007/s11276-009-0229-3},
doi = {10.1007/S11276-009-0229-3},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/winet/ReddyBRC10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MaeiSBS10,
author = {Hamid Reza Maei and
Csaba Szepesv{\'{a}}ri and
Shalabh Bhatnagar and
Richard S. Sutton},
editor = {Johannes F{\"{u}}rnkranz and
Thorsten Joachims},
title = {Toward Off-Policy Learning Control with Function Approximation},
booktitle = {Proceedings of the 27th International Conference on Machine Learning
(ICML-10), June 21-24, 2010, Haifa, Israel},
pages = {719--726},
publisher = {Omnipress},
year = {2010},
url = {https://icml.cc/Conferences/2010/papers/627.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MaeiSBS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/BhatnagarSGL09,
author = {Shalabh Bhatnagar and
Richard S. Sutton and
Mohammad Ghavamzadeh and
Mark Lee},
title = {Natural actor-critic algorithms},
journal = {Autom.},
volume = {45},
number = {11},
pages = {2471--2482},
year = {2009},
url = {https://doi.org/10.1016/j.automatica.2009.07.008},
doi = {10.1016/J.AUTOMATICA.2009.07.008},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/BhatnagarSGL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/icl/BhatnagarP09,
author = {Shalabh Bhatnagar and
Rajesh Kumar Patro},
title = {A proof of convergence of the {B-RED} and {P-RED} algorithms for random
early detection},
journal = {{IEEE} Commun. Lett.},
volume = {13},
number = {10},
pages = {809--811},
year = {2009},
url = {https://doi.org/10.1109/LCOMM.2009.091276},
doi = {10.1109/LCOMM.2009.091276},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/icl/BhatnagarP09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pe/PatroB09,
author = {Rajesh Kumar Patro and
Shalabh Bhatnagar},
title = {A probabilistic constrained nonlinear optimization framework to optimize
{RED} parameters},
journal = {Perform. Evaluation},
volume = {66},
number = {2},
pages = {81--104},
year = {2009},
url = {https://doi.org/10.1016/j.peva.2008.09.003},
doi = {10.1016/J.PEVA.2008.09.003},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pe/PatroB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/BhatnagarKM09,
author = {Shalabh Bhatnagar and
Karmeshu and
Vivek Kumar Mishra},
title = {Optimal parameter trajectory estimation in parameterized SDEs: An
algorithmic procedure},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {19},
number = {2},
pages = {8:1--8:27},
year = {2009},
url = {https://doi.org/10.1145/1502787.1502791},
doi = {10.1145/1502787.1502791},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/BhatnagarKM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/YaoBS09,
author = {Hengshuai Yao and
Shalabh Bhatnagar and
Csaba Szepesv{\'{a}}ri},
title = {{LMS-2:} Towards an algorithm that is as cheap as {LMS} and almost
as efficient as {RLS}},
booktitle = {Proceedings of the 48th {IEEE} Conference on Decision and Control,
{CDC} 2009, combined withe the 28th Chinese Control Conference, December
16-18, 2009, Shanghai, China},
pages = {1181--1188},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/CDC.2009.5400370},
doi = {10.1109/CDC.2009.5400370},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/YaoBS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SuttonMPBSSW09,
author = {Richard S. Sutton and
Hamid Reza Maei and
Doina Precup and
Shalabh Bhatnagar and
David Silver and
Csaba Szepesv{\'{a}}ri and
Eric Wiewiora},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Fast gradient-descent methods for temporal-difference learning with
linear function approximation},
booktitle = {Proceedings of the 26th Annual International Conference on Machine
Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009},
series = {{ACM} International Conference Proceeding Series},
volume = {382},
pages = {993--1000},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553501},
doi = {10.1145/1553374.1553501},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/SuttonMPBSSW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MaeiSBPSS09,
author = {Hamid Reza Maei and
Csaba Szepesv{\'{a}}ri and
Shalabh Bhatnagar and
Doina Precup and
David Silver and
Richard S. Sutton},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Convergent Temporal-Difference Learning with Arbitrary Smooth Function
Approximation},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {1204--1212},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/3a15c7d0bbe60300a39f76f8a5ba6896-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MaeiSBPSS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/YaoSBDS09,
author = {Hengshuai Yao and
Richard S. Sutton and
Shalabh Bhatnagar and
Diao Dongcui and
Csaba Szepesv{\'{a}}ri},
editor = {Yoshua Bengio and
Dale Schuurmans and
John D. Lafferty and
Christopher K. I. Williams and
Aron Culotta},
title = {Multi-Step Dyna Planning for Policy Evaluation and Control},
booktitle = {Advances in Neural Information Processing Systems 22: 23rd Annual
Conference on Neural Information Processing Systems 2009. Proceedings
of a meeting held 7-10 December 2009, Vancouver, British Columbia,
Canada},
pages = {2187--2195},
publisher = {Curran Associates, Inc.},
year = {2009},
url = {https://proceedings.neurips.cc/paper/2009/hash/c52f1bd66cc19d05628bd8bf27af3ad6-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/YaoSBDS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:reference/dataware/ViswanathMB09,
author = {P. Viswanath and
M. Narasimha Murty and
Shalabh Bhatnagar},
editor = {John Wang},
title = {Pattern Synthesis for Nonparametric Pattern Recognition},
booktitle = {Encyclopedia of Data Warehousing and Mining, Second Edition {(4} Volumes)},
pages = {1511--1516},
publisher = {{IGI} Global},
year = {2009},
url = {http://www.igi-global.com/Bookstore/Chapter.aspx?TitleId=11020},
timestamp = {Wed, 12 Jul 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/reference/dataware/ViswanathMB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/BhatnagarB08,
author = {Shalabh Bhatnagar and
K. Mohan Babu},
title = {New algorithms of the Q-learning type},
journal = {Autom.},
volume = {44},
number = {4},
pages = {1111--1119},
year = {2008},
url = {https://doi.org/10.1016/j.automatica.2007.09.009},
doi = {10.1016/J.AUTOMATICA.2007.09.009},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/BhatnagarB08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mms/VelusamyGBV08,
author = {Sudha Velusamy and
Lakshmi Gopal and
Shalabh Bhatnagar and
Sridhar Varadarajan},
title = {An efficient ad recommendation system for {TV} programs},
journal = {Multim. Syst.},
volume = {14},
number = {2},
pages = {73--87},
year = {2008},
url = {https://doi.org/10.1007/s00530-008-0117-1},
doi = {10.1007/S00530-008-0117-1},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mms/VelusamyGBV08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simulation/BhatnagarA08,
author = {Shalabh Bhatnagar and
Mohammed Shahid Abdulla},
title = {Simulation-Based Optimization Algorithms for Finite-Horizon Markov
Decision Processes},
journal = {Simul.},
volume = {84},
number = {12},
pages = {577--600},
year = {2008},
url = {https://doi.org/10.1177/0037549708098120},
doi = {10.1177/0037549708098120},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simulation/BhatnagarA08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/VelusamyBBS08,
author = {Sudha Velusamy and
Shalabh Bhatnagar and
S. V. Basavaraja and
V. Sridhar},
title = {{SPSA} based feature relevance estimation for video retrieval},
booktitle = {International Workshop on Multimedia Signal Processing, {MMSP} 2008,
October 8-10, 2008, Shangri-la Hotel, Cairns, Queensland, Australia},
pages = {598--603},
publisher = {{IEEE} Signal Processing Society},
year = {2008},
url = {https://doi.org/10.1109/MMSP.2008.4665147},
doi = {10.1109/MMSP.2008.4665147},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mmsp/VelusamyBBS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/netcoop/KolavaliB08,
author = {Sudha Rani Kolavali and
Shalabh Bhatnagar},
editor = {Eitan Altman and
Augustin Chaintreau},
title = {Ant Colony Optimization Algorithms for Shortest Path Problems},
booktitle = {Network Control and Optimization, Second Euro-NF Workshop, {NET-COOP}
2008, Paris, France, September 8-10, 2008. Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {5425},
pages = {37--44},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-642-00393-6\_5},
doi = {10.1007/978-3-642-00393-6\_5},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/netcoop/KolavaliB08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/deds/AbdullaB07,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
title = {Reinforcement Learning Based Algorithms for Average Cost Markov Decision
Processes},
journal = {Discret. Event Dyn. Syst.},
volume = {17},
number = {1},
pages = {23--52},
year = {2007},
url = {https://doi.org/10.1007/s10626-006-0003-y},
doi = {10.1007/S10626-006-0003-Y},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/deds/AbdullaB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/isci/DukkipatiBM07,
author = {Ambedkar Dukkipati and
Shalabh Bhatnagar and
M. Narasimha Murty},
title = {Gelfand-Yaglom-Perez theorem for generalized relative entropy functionals},
journal = {Inf. Sci.},
volume = {177},
number = {24},
pages = {5707--5714},
year = {2007},
url = {https://doi.org/10.1016/j.ins.2007.07.017},
doi = {10.1016/J.INS.2007.07.017},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/isci/DukkipatiBM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/Bhatnagar07,
author = {Shalabh Bhatnagar},
title = {Adaptive Newton-based multivariate smoothed functional algorithms
for simulation optimization},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {18},
number = {1},
pages = {2:1--2:35},
year = {2007},
url = {https://doi.org/10.1145/1315575.1315577},
doi = {10.1145/1315575.1315577},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/Bhatnagar07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acc/AbdullaB07,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
title = {Parametrized Actor-Critic Algorithms for Finite-Horizon MDPs},
booktitle = {American Control Conference, {ACC} 2007, New York, NY, USA, 9-13 July,
2007},
pages = {534--539},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ACC.2007.4282587},
doi = {10.1109/ACC.2007.4282587},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acc/AbdullaB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acc/AbdullaB07a,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
title = {Solving MDPs using Two-timescale Simulated Annealing with Multiplicative
Weights},
booktitle = {American Control Conference, {ACC} 2007, New York, NY, USA, 9-13 July,
2007},
pages = {2428--2433},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ACC.2007.4282586},
doi = {10.1109/ACC.2007.4282586},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acc/AbdullaB07a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/VemuBH07,
author = {Koteswara Rao Vemu and
Shalabh Bhatnagar and
N. Hemachandra},
title = {Link route pricing for enhanced QoS},
booktitle = {46th {IEEE} Conference on Decision and Control, {CDC} 2007, New Orleans,
LA, USA, December 12-14, 2007},
pages = {1504--1509},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CDC.2007.4434595},
doi = {10.1109/CDC.2007.4434595},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/VemuBH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/MishraBH07,
author = {Vivek Kumar Mishra and
Shalabh Bhatnagar and
N. Hemachandra},
title = {Discrete parameter simulation optimization algorithms with applications
to admission control with dependent service times},
booktitle = {46th {IEEE} Conference on Decision and Control, {CDC} 2007, New Orleans,
LA, USA, December 12-14, 2007},
pages = {2986--2991},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CDC.2007.4434229},
doi = {10.1109/CDC.2007.4434229},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/MishraBH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/AbdullaB07,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
title = {Network flow-control using asynchronous stochastic approximation},
booktitle = {46th {IEEE} Conference on Decision and Control, {CDC} 2007, New Orleans,
LA, USA, December 12-14, 2007},
pages = {5857--5862},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CDC.2007.4434593},
doi = {10.1109/CDC.2007.4434593},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/AbdullaB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/euroitv/VelusamyGVB07,
author = {Sudha Velusamy and
Lakshmi Gopal and
Sridhar Varadarajan and
Shalabh Bhatnagar},
editor = {Pablo C{\'{e}}sar and
Konstantinos Chorianopoulos and
Jens F. Jensen},
title = {Fuzzy Clustering Based Ad Recommendation for {TV} Programs},
booktitle = {Interactive {TV:} a Shared Experience, 5th European Conference, EuroITV
2007, Amsterdam, The Netherlands, May 24-25, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4471},
pages = {175--184},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-72559-6\_19},
doi = {10.1007/978-3-540-72559-6\_19},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/euroitv/VelusamyGVB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdcit/ChaturvediRB07,
author = {Vijay Prakash Chaturvedi and
V. Rakesh and
Shalabh Bhatnagar},
editor = {Tomasz Janowski and
Hrushikesha Mohanty},
title = {An Efficient and Optimized Bluetooth Scheduling Algorithm for Piconets},
booktitle = {Distributed Computing and Internet Technology, 4th International Conference,
{ICDCIT} 2007, Bangalore, India, December 17-20, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4882},
pages = {19--30},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-77115-9\_2},
doi = {10.1007/978-3-540-77115-9\_2},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdcit/ChaturvediRB07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdcit/VemuBH07,
author = {Koteswara Rao Vemu and
Shalabh Bhatnagar and
N. Hemachandra},
editor = {Tomasz Janowski and
Hrushikesha Mohanty},
title = {An Optimal Weighted-Average Congestion Based Pricing Scheme for Enhanced
QoS},
booktitle = {Distributed Computing and Internet Technology, 4th International Conference,
{ICDCIT} 2007, Bangalore, India, December 17-20, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4882},
pages = {135--145},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-77115-9\_14},
doi = {10.1007/978-3-540-77115-9\_14},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdcit/VemuBH07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BhatnagarSGL07,
author = {Shalabh Bhatnagar and
Richard S. Sutton and
Mohammad Ghavamzadeh and
Mark Lee},
editor = {John C. Platt and
Daphne Koller and
Yoram Singer and
Sam T. Roweis},
title = {Incremental Natural Actor-Critic Algorithms},
booktitle = {Advances in Neural Information Processing Systems 20, Proceedings
of the Twenty-First Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 3-6, 2007},
pages = {105--112},
publisher = {Curran Associates, Inc.},
year = {2007},
url = {https://proceedings.neurips.cc/paper/2007/hash/6883966fd8f918a4aa29be29d2c386fb-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/BhatnagarSGL07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/BhatnagarP06,
author = {Shalabh Bhatnagar and
J. Ranjan Panigrahi},
title = {Actor-critic algorithms for hierarchical Markov decision processes},
journal = {Autom.},
volume = {42},
number = {4},
pages = {637--644},
year = {2006},
url = {https://doi.org/10.1016/j.automatica.2005.12.010},
doi = {10.1016/J.AUTOMATICA.2005.12.010},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/BhatnagarP06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/BhatnagarBA06,
author = {Shalabh Bhatnagar and
Vivek S. Borkar and
Madhukar Akarapu},
title = {A Simulation-Based Algorithm for Ergodic Control of Markov Chains
Conditioned on Rare Events},
journal = {J. Mach. Learn. Res.},
volume = {7},
pages = {1937--1962},
year = {2006},
url = {http://jmlr.org/papers/v7/bhatnagar06a.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/BhatnagarBA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/prl/ViswanathMB06,
author = {P. Viswanath and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Partition based pattern synthesis technique with efficient algorithms
for nearest neighbor classification},
journal = {Pattern Recognit. Lett.},
volume = {27},
number = {14},
pages = {1714--1724},
year = {2006},
url = {https://doi.org/10.1016/j.patrec.2006.04.015},
doi = {10.1016/J.PATREC.2006.04.015},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/prl/ViswanathMB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/telsys/VaidyaB06,
author = {Rahul Vaidya and
Shalabh Bhatnagar},
title = {Robust optimization of Random Early Detection},
journal = {Telecommun. Syst.},
volume = {33},
number = {4},
pages = {291--316},
year = {2006},
url = {https://doi.org/10.1007/s11235-006-9020-2},
doi = {10.1007/S11235-006-9020-2},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/telsys/VaidyaB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/PatroB06,
author = {Rajesh Kumar Patro and
Shalabh Bhatnagar},
title = {A Four-Timescale Algorithm for Constrained Stochastic Optimization
of {RED}},
booktitle = {45th {IEEE} Conference on Decision and Control, {CDC} 2006, San Diego,
CA, USA, December 13-15, 2006},
pages = {1930--1935},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/CDC.2006.377655},
doi = {10.1109/CDC.2006.377655},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/PatroB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/BhatnagarA06,
author = {Shalabh Bhatnagar and
Mohammed Shahid Abdulla},
title = {A Reinforcement Learning Based Algorithm for Finite Horizon Markov
Decision Processes},
booktitle = {45th {IEEE} Conference on Decision and Control, {CDC} 2006, San Diego,
CA, USA, December 13-15, 2006},
pages = {5519--5524},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/CDC.2006.377190},
doi = {10.1109/CDC.2006.377190},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/BhatnagarA06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wsc/AbdullaB06,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
editor = {L. Felipe Perrone and
Barry Lawson and
Jason Liu and
Frederick P. Wieland},
title = {{SPSA} algorithms with measurement reuse},
booktitle = {Proceedings of the Winter Simulation Conference {WSC} 2006, Monterey,
California, USA, December 3-6, 2006},
pages = {320--328},
publisher = {{IEEE} Computer Society},
year = {2006},
url = {https://doi.org/10.1109/WSC.2006.323089},
doi = {10.1109/WSC.2006.323089},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/wsc/AbdullaB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-cs-0601080,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {On Measure Theoretic definitions of Generalized Information Measures
and Maximum Entropy Prescriptions},
journal = {CoRR},
volume = {abs/cs/0601080},
year = {2006},
url = {http://arxiv.org/abs/cs/0601080},
eprinttype = {arXiv},
eprint = {cs/0601080},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-cs-0601080.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pr/ViswanathMB05,
author = {P. Viswanath and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Overlap pattern synthesis with an efficient nearest neighbor classifier},
journal = {Pattern Recognit.},
volume = {38},
number = {8},
pages = {1187--1195},
year = {2005},
url = {https://doi.org/10.1016/j.patcog.2004.10.007},
doi = {10.1016/J.PATCOG.2004.10.007},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pr/ViswanathMB05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simulation/BhatnagarK05,
author = {Shalabh Bhatnagar and
Hemant J. Kowshik},
title = {A Discrete Parameter Stochastic Approximation Algorithm for Simulation
Optimization},
journal = {Simul.},
volume = {81},
number = {11},
pages = {757--772},
year = {2005},
url = {https://doi.org/10.1177/0037549705062294},
doi = {10.1177/0037549705062294},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simulation/BhatnagarK05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/telsys/BhatnagarR05,
author = {Shalabh Bhatnagar and
I. Bala Bhaskar Reddy},
title = {Optimal Threshold Policies for Admission Control in Communication
Networks via Discrete Parameter Stochastic Approximation},
journal = {Telecommun. Syst.},
volume = {29},
number = {1},
pages = {9--31},
year = {2005},
url = {https://doi.org/10.1007/s11235-005-6629-5},
doi = {10.1007/S11235-005-6629-5},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/telsys/BhatnagarR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/Bhatnagar05,
author = {Shalabh Bhatnagar},
title = {Adaptive multivariate three-timescale stochastic approximation algorithms
for simulation based optimization},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {15},
number = {1},
pages = {74--107},
year = {2005},
url = {https://doi.org/10.1145/1044322.1044326},
doi = {10.1145/1044322.1044326},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/Bhatnagar05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cec/DukkipatiMB05,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Information theoretic justification of Boltzmann selection and its
generalization to Tsallis case},
booktitle = {Proceedings of the {IEEE} Congress on Evolutionary Computation, {CEC}
2005, 2-4 September 2005, Edinburgh, {UK}},
pages = {1667--1674},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/CEC.2005.1554889},
doi = {10.1109/CEC.2005.1554889},
timestamp = {Thu, 16 Dec 2021 13:59:05 +0100},
biburl = {https://dblp.org/rec/conf/cec/DukkipatiMB05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ifip12/AbdullaB05,
author = {Mohammed Shahid Abdulla and
Shalabh Bhatnagar},
editor = {Daoliang Li and
Baoji Wang},
title = {Solution of Mdps Using Simulation-Based Value Iteration},
booktitle = {Artificial Intelligence Applications and Innovations - {IFIP} {TC12}
{WG12.5} - Second {IFIP} Conference on Artificial Intelligence Applications
and Innovations (AIAI2005), September 7-9, 2005, Beijing, China},
series = {{IFIP}},
volume = {187},
pages = {765--775},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/0-387-29295-0\_83},
doi = {10.1007/0-387-29295-0\_83},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ifip12/AbdullaB05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isit/DukkipatiMB05,
author = {Ambedkar Dukkipati and
Narasimha Murty Musti and
Shalabh Bhatnagar},
title = {Properties of Kullback-Leibler cross-entropy minimization in nonextensive
framework},
booktitle = {Proceedings of the 2005 {IEEE} International Symposium on Information
Theory, {ISIT} 2005, Adelaide, South Australia, Australia, 4-9 September
2005},
pages = {2374--2378},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ISIT.2005.1523773},
doi = {10.1109/ISIT.2005.1523773},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isit/DukkipatiMB05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-cs-0511078,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Uniqueness of Nonextensive entropy under Renyi's Recipe},
journal = {CoRR},
volume = {abs/cs/0511078},
year = {2005},
url = {http://arxiv.org/abs/cs/0511078},
eprinttype = {arXiv},
eprint = {cs/0511078},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-cs-0511078.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/inffus/ViswanathMB04,
author = {P. Viswanath and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Fusion of multiple approximate nearest neighbor classifiers for fast
and efficient classification},
journal = {Inf. Fusion},
volume = {5},
number = {4},
pages = {239--250},
year = {2004},
url = {https://doi.org/10.1016/j.inffus.2004.02.003},
doi = {10.1016/J.INFFUS.2004.02.003},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/inffus/ViswanathMB04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/BhatnagarK04,
author = {Shalabh Bhatnagar and
Shishir Kumar},
title = {A simultaneous perturbation stochastic approximation-based actor-critic
algorithm for Markov decision processes},
journal = {{IEEE} Trans. Autom. Control.},
volume = {49},
number = {4},
pages = {592--598},
year = {2004},
url = {https://doi.org/10.1109/TAC.2004.825622},
doi = {10.1109/TAC.2004.825622},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/BhatnagarK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/PanigrahiB04,
author = {Jnana Ranjan Panigrahi and
Shalabh Bhatnagar},
title = {Hierarchical decision making in semiconductor fabs using multi-time
scale Markov decision processes},
booktitle = {43rd {IEEE} Conference on Decision and Control, {CDC} 2004, Nassau,
Bahamas, December 14-17, 2004},
pages = {4387--4392},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/CDC.2004.1429441},
doi = {10.1109/CDC.2004.1429441},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/PanigrahiB04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cec/DukkipatiMB04,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Cauchy annealing schedule: an annealing schedule for Boltzmann selection
scheme in evolutionary algorithms},
booktitle = {Proceedings of the {IEEE} Congress on Evolutionary Computation, {CEC}
2004, 19-23 June 2004, Portland, OR, {USA}},
pages = {55--62},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/CEC.2004.1330837},
doi = {10.1109/CEC.2004.1330837},
timestamp = {Thu, 16 Dec 2021 13:58:46 +0100},
biburl = {https://dblp.org/rec/conf/cec/DukkipatiMB04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/ViswanathMB04,
author = {P. Viswanath and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {A Pattern Synthesis Technique with an Efficient Nearest Neighbor Classifier
for Binary Pattern Recognition},
booktitle = {17th International Conference on Pattern Recognition, {ICPR} 2004,
Cambridge, UK, August 23-26, 2004},
pages = {416--419},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.org/10.1109/ICPR.2004.1333791},
doi = {10.1109/ICPR.2004.1333791},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpr/ViswanathMB04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/cs-AI-0407037,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Generalized Evolutionary Algorithm based on Tsallis Statistics},
journal = {CoRR},
volume = {cs.AI/0407037},
year = {2004},
url = {http://arxiv.org/abs/cs.AI/0407037},
doi = {10.48550/ARXIV.CS/0407037},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/cs-AI-0407037.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/cs-AI-0408055,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Cauchy Annealing Schedule: An Annealing Schedule for Boltzmann Selection
Scheme in Evolutionary Algorithms},
journal = {CoRR},
volume = {cs.AI/0408055},
year = {2004},
url = {http://arxiv.org/abs/cs.AI/0408055},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/cs-AI-0408055.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/simulation/BhatnagarB03,
author = {Shalabh Bhatnagar and
Vivek S. Borkar},
title = {Multiscale Chaotic {SPSA} and Smoothed Functional Algorithms for Simulation
Optimization},
journal = {Simul.},
volume = {79},
number = {10},
pages = {568--580},
year = {2003},
url = {https://doi.org/10.1177/0037549703039988},
doi = {10.1177/0037549703039988},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/simulation/BhatnagarB03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomacs/BhatnagarFMW03,
author = {Shalabh Bhatnagar and
Michael C. Fu and
Steven I. Marcus and
I{-}Jeng Wang},
title = {Two-timescale simultaneous perturbation stochastic approximation using
deterministic perturbation sequences},
journal = {{ACM} Trans. Model. Comput. Simul.},
volume = {13},
number = {2},
pages = {180--209},
year = {2003},
url = {https://doi.org/10.1145/858481.858486},
doi = {10.1145/858481.858486},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tomacs/BhatnagarFMW03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cec/DukkipatiMB03,
author = {Ambedkar Dukkipati and
M. Narasimha Murty and
Shalabh Bhatnagar},
title = {Quotient evolutionary space: abstraction of evolutionary process w.r.t
macroscopic properties},
booktitle = {Proceedings of the {IEEE} Congress on Evolutionary Computation, {CEC}
2003, Canberra, Australia, December 8-12, 2003},
pages = {846--853},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/CEC.2003.1299755},
doi = {10.1109/CEC.2003.1299755},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cec/DukkipatiMB03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/automatica/CaoRBFM02,
author = {Xi{-}Ren Cao and
Zhiyuan Ren and
Shalabh Bhatnagar and
Michael C. Fu and
Steven I. Marcus},
title = {A time aggregation approach to Markov decision processes},
journal = {Autom.},
volume = {38},
number = {6},
pages = {929--943},
year = {2002},
url = {https://doi.org/10.1016/S0005-1098(01)00282-5},
doi = {10.1016/S0005-1098(01)00282-5},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/automatica/CaoRBFM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ton/BhatnagarFMF01,
author = {Shalabh Bhatnagar and
Michael C. Fu and
Steven I. Marcus and
Pedram Jaefari Fard},
title = {Optimal structured feedback policies for {ABR} flow control using
two-timescale {SPSA}},
journal = {{IEEE/ACM} Trans. Netw.},
volume = {9},
number = {4},
pages = {479--491},
year = {2001},
url = {https://doi.org/10.1109/90.944345},
doi = {10.1109/90.944345},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ton/BhatnagarFMF01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/BhatnagarB95,
author = {Shalabh Bhatnagar and
Vivek S. Borkar},
title = {A Convex Analytic Framework for Ergodic Control of Semi-Markov Processes},
journal = {Math. Oper. Res.},
volume = {20},
number = {4},
pages = {923--936},
year = {1995},
url = {https://doi.org/10.1287/moor.20.4.923},
doi = {10.1287/MOOR.20.4.923},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/BhatnagarB95.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2024-04-21 17:52 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
