Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Brett Daley
@article{DBLP:journals/corr/abs-2402-03903,
author = {Brett Daley and
Martha White and
Marlos C. Machado},
title = {Compound Returns Reduce Variance in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2402.03903},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.03903},
doi = {10.48550/ARXIV.2402.03903},
eprinttype = {arXiv},
eprint = {2402.03903},
timestamp = {Mon, 12 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-03903.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/LyuBXDA23,
author = {Xueguang Lyu and
Andrea Baisero and
Yuchen Xiao and
Brett Daley and
Christopher Amato},
title = {On Centralized Critics in Multi-Agent Reinforcement Learning},
journal = {J. Artif. Intell. Res.},
volume = {77},
pages = {295--354},
year = {2023},
url = {https://doi.org/10.1613/jair.1.14386},
doi = {10.1613/JAIR.1.14386},
timestamp = {Sun, 18 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/LyuBXDA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DaleyWAM23,
author = {Brett Daley and
Martha White and
Christopher Amato and
Marlos C. Machado},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {6818--6835},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/daley23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/DaleyWAM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11321,
author = {Brett Daley and
Martha White and
Christopher Amato and
Marlos C. Machado},
title = {Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning},
journal = {CoRR},
volume = {abs/2301.11321},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.11321},
doi = {10.48550/ARXIV.2301.11321},
eprinttype = {arXiv},
eprint = {2301.11321},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-11321.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/BaiseroDA22,
author = {Andrea Baisero and
Brett Daley and
Christopher Amato},
editor = {James Cussens and
Kun Zhang},
title = {Asymmetric {DQN} for partially observable reinforcement learning},
booktitle = {Uncertainty in Artificial Intelligence, Proceedings of the Thirty-Eighth
Conference on Uncertainty in Artificial Intelligence, {UAI} 2022,
1-5 August 2022, Eindhoven, The Netherlands},
series = {Proceedings of Machine Learning Research},
volume = {180},
pages = {107--117},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v180/baisero22a.html},
timestamp = {Sat, 15 Oct 2022 12:08:13 +0200},
biburl = {https://dblp.org/rec/conf/uai/BaiseroDA22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-01896,
author = {Brett Daley and
Isaac Chan},
title = {Adaptive Tree Backup Algorithms for Temporal-Difference Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2206.01896},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.01896},
doi = {10.48550/ARXIV.2206.01896},
eprinttype = {arXiv},
eprint = {2206.01896},
timestamp = {Mon, 13 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-01896.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/LyuXDA21,
author = {Xueguang Lyu and
Yuchen Xiao and
Brett Daley and
Christopher Amato},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement
Learning},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {844--852},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p844.pdf},
doi = {10.5555/3463952.3464053},
timestamp = {Wed, 20 Jul 2022 17:03:47 +0200},
biburl = {https://dblp.org/rec/conf/atal/LyuXDA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/DaleyHA21,
author = {Brett Daley and
Cameron Hickert and
Christopher Amato},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy
Reinforcement Learning},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {1486--1488},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1486.pdf},
doi = {10.5555/3463952.3464134},
timestamp = {Wed, 20 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/DaleyHA21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04402,
author = {Xueguang Lyu and
Yuchen Xiao and
Brett Daley and
Christopher Amato},
title = {Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2102.04402},
year = {2021},
url = {https://arxiv.org/abs/2102.04402},
eprinttype = {arXiv},
eprint = {2102.04402},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04402.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-11319,
author = {Brett Daley and
Cameron Hickert and
Christopher Amato},
title = {Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy
Reinforcement Learning},
journal = {CoRR},
volume = {abs/2102.11319},
year = {2021},
url = {https://arxiv.org/abs/2102.11319},
eprinttype = {arXiv},
eprint = {2102.11319},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-11319.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-05449,
author = {Brett Daley and
Christopher Amato},
title = {Investigating Alternatives to the Root Mean Square for Adaptive Gradient
Methods},
journal = {CoRR},
volume = {abs/2106.05449},
year = {2021},
url = {https://arxiv.org/abs/2106.05449},
eprinttype = {arXiv},
eprint = {2106.05449},
timestamp = {Tue, 15 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-05449.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-01264,
author = {Brett Daley and
Christopher Amato},
title = {Human-Level Control without Server-Grade Hardware},
journal = {CoRR},
volume = {abs/2111.01264},
year = {2021},
url = {https://arxiv.org/abs/2111.01264},
eprinttype = {arXiv},
eprint = {2111.01264},
timestamp = {Fri, 05 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-01264.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-03421,
author = {Brett Daley and
Christopher Amato},
title = {Virtual Replay Cache},
journal = {CoRR},
volume = {abs/2112.03421},
year = {2021},
url = {https://arxiv.org/abs/2112.03421},
eprinttype = {arXiv},
eprint = {2112.03421},
timestamp = {Mon, 13 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-03421.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2112-12281,
author = {Brett Daley and
Christopher Amato},
title = {Improving the Efficiency of Off-Policy Reinforcement Learning by Accounting
for Past Decisions},
journal = {CoRR},
volume = {abs/2112.12281},
year = {2021},
url = {https://arxiv.org/abs/2112.12281},
eprinttype = {arXiv},
eprint = {2112.12281},
timestamp = {Tue, 04 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2112-12281.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/NguyenDSAP20,
author = {Hai Nguyen and
Brett Daley and
Xinchao Song and
Christopher Amato and
Robert Platt},
editor = {Jens Kober and
Fabio Ramos and
Claire J. Tomlin},
title = {Belief-Grounded Networks for Accelerated Robot Learning under Partial
Observability},
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 = {1640--1653},
publisher = {{PMLR}},
year = {2020},
url = {https://proceedings.mlr.press/v155/nguyen21a.html},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/NguyenDSAP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01356,
author = {Brett Daley and
Christopher Amato},
title = {Expectigrad: Fast Stochastic Optimization with Robust Convergence
Properties},
journal = {CoRR},
volume = {abs/2010.01356},
year = {2020},
url = {https://arxiv.org/abs/2010.01356},
eprinttype = {arXiv},
eprint = {2010.01356},
timestamp = {Mon, 12 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01356.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-09170,
author = {Hai Nguyen and
Brett Daley and
Xinchao Song and
Christopher Amato and
Robert Platt},
title = {Belief-Grounded Networks for Accelerated Robot Learning under Partial
Observability},
journal = {CoRR},
volume = {abs/2010.09170},
year = {2020},
url = {https://arxiv.org/abs/2010.09170},
eprinttype = {arXiv},
eprint = {2010.09170},
timestamp = {Mon, 07 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-09170.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DaleyA19,
author = {Brett Daley and
Christopher Amato},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Reconciling {\(\lambda\)}-Returns with Experience Replay},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {1131--1140},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/9f396fe44e7c05c16873b05ec425cbad-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/DaleyA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1810-09967,
author = {Brett Daley and
Christopher Amato},
title = {Efficient Eligibility Traces for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1810.09967},
year = {2018},
url = {http://arxiv.org/abs/1810.09967},
eprinttype = {arXiv},
eprint = {1810.09967},
timestamp = {Wed, 31 Oct 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1810-09967.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wosp/UkidavePYKMCMDMK15,
author = {Yash Ukidave and
Fanny Nina Paravecino and
Leiming Yu and
Charu Kalra and
Amir Momeni and
Zhongliang Chen and
Nick Materise and
Brett Daley and
Perhaad Mistry and
David R. Kaeli},
editor = {Lizy K. John and
Connie U. Smith and
Kai Sachs and
Catalina M. Llad{\'{o}}},
title = {{NUPAR:} {A} Benchmark Suite for Modern {GPU} Architectures},
booktitle = {Proceedings of the 6th {ACM/SPEC} International Conference on Performance
Engineering, Austin, TX, USA, January 31 - February 4, 2015},
pages = {253--264},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2668930.2688046},
doi = {10.1145/2668930.2688046},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/wosp/UkidavePYKMCMDMK15.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 17:00 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:
