Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Hado van Hasselt
@article{DBLP:journals/corr/abs-2402-18762,
author = {Clare Lyle and
Zeyu Zheng and
Khimya Khetarpal and
Hado van Hasselt and
Razvan Pascanu and
James Martens and
Will Dabney},
title = {Disentangling the Causes of Plasticity Loss in Neural Networks},
journal = {CoRR},
volume = {abs/2402.18762},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.18762},
doi = {10.48550/ARXIV.2402.18762},
eprinttype = {arXiv},
eprint = {2402.18762},
timestamp = {Tue, 26 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-18762.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SchmittSH23,
author = {Simon Schmitt and
John Shawe{-}Taylor and
Hado van Hasselt},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {Exploration via Epistemic Value Estimation},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {9742--9751},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i8.26164},
doi = {10.1609/AAAI.V37I8.26164},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/SchmittSH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Kapturowski0JRH23,
author = {Steven Kapturowski and
Victor Campos and
Ray Jiang and
Nemanja Rakicevic and
Hado van Hasselt and
Charles Blundell and
Adri{\`{a}} Puigdom{\`{e}}nech Badia},
title = {Human-level Atari 200x faster},
booktitle = {The Eleventh International Conference on Learning Representations,
{ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
year = {2023},
url = {https://openreview.net/pdf?id=JtC6yOHRoJJ},
timestamp = {Fri, 30 Jun 2023 14:38:38 +0200},
biburl = {https://dblp.org/rec/conf/iclr/Kapturowski0JRH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Abel0RPHS23,
author = {David Abel and
Andr{\'{e}} Barreto and
Benjamin Van Roy and
Doina Precup and
Hado Philip van Hasselt and
Satinder Singh},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {A Definition of Continual Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/9d8cf1247786d6dfeefeeb53b8b5f6d7-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/Abel0RPHS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FlennerhagZOH0S23,
author = {Sebastian Flennerhag and
Tom Zahavy and
Brendan O'Donoghue and
Hado Philip van Hasselt and
Andr{\'{a}}s Gy{\"{o}}rgy and
Satinder Singh},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Optimistic Meta-Gradients},
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
LA, USA, December 10 - 16, 2023},
year = {2023},
url = {http://papers.nips.cc/paper\_files/paper/2023/hash/b46bc1449205888e1883f692aff1a252-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/FlennerhagZOH0S23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-03236,
author = {Sebastian Flennerhag and
Tom Zahavy and
Brendan O'Donoghue and
Hado van Hasselt and
Andr{\'{a}}s Gy{\"{o}}rgy and
Satinder Singh},
title = {Optimistic Meta-Gradients},
journal = {CoRR},
volume = {abs/2301.03236},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.03236},
doi = {10.48550/ARXIV.2301.03236},
eprinttype = {arXiv},
eprint = {2301.03236},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-03236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-04250,
author = {Chentian Jiang and
Nan Rosemary Ke and
Hado van Hasselt},
title = {Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration},
journal = {CoRR},
volume = {abs/2302.04250},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.04250},
doi = {10.48550/ARXIV.2302.04250},
eprinttype = {arXiv},
eprint = {2302.04250},
timestamp = {Fri, 10 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-04250.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-04012,
author = {Simon Schmitt and
John Shawe{-}Taylor and
Hado van Hasselt},
title = {Exploration via Epistemic Value Estimation},
journal = {CoRR},
volume = {abs/2303.04012},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.04012},
doi = {10.48550/ARXIV.2303.04012},
eprinttype = {arXiv},
eprint = {2303.04012},
timestamp = {Wed, 15 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-04012.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11044,
author = {David Abel and
Andr{\'{e}} Barreto and
Hado van Hasselt and
Benjamin Van Roy and
Doina Precup and
Satinder Singh},
title = {On the Convergence of Bounded Agents},
journal = {CoRR},
volume = {abs/2307.11044},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.11044},
doi = {10.48550/ARXIV.2307.11044},
eprinttype = {arXiv},
eprint = {2307.11044},
timestamp = {Wed, 26 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-11044.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-11046,
author = {David Abel and
Andr{\'{e}} Barreto and
Benjamin Van Roy and
Doina Precup and
Hado van Hasselt and
Satinder Singh},
title = {A Definition of Continual Reinforcement Learning},
journal = {CoRR},
volume = {abs/2307.11046},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.11046},
doi = {10.48550/ARXIV.2307.11046},
eprinttype = {arXiv},
eprint = {2307.11046},
timestamp = {Wed, 26 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-11046.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-01072,
author = {Eduardo Pignatelli and
Johan Ferret and
Matthieu Geist and
Thomas Mesnard and
Hado van Hasselt and
Laura Toni},
title = {A Survey of Temporal Credit Assignment in Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2312.01072},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.01072},
doi = {10.48550/ARXIV.2312.01072},
eprinttype = {arXiv},
eprint = {2312.01072},
timestamp = {Fri, 08 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-01072.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/JiangZC0H22,
author = {Ray Jiang and
Shangtong Zhang and
Veronica Chelu and
Adam White and
Hado van Hasselt},
title = {Learning Expected Emphatic Traces for Deep {RL}},
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 = {7015--7023},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i6.20660},
doi = {10.1609/AAAI.V36I6.20660},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/JiangZC0H22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KirschFHFOC22,
author = {Louis Kirsch and
Sebastian Flennerhag and
Hado van Hasselt and
Abram L. Friesen and
Junhyuk Oh and
Yutian Chen},
title = {Introducing Symmetries to Black Box Meta Reinforcement Learning},
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 = {7202--7210},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i7.20681},
doi = {10.1609/AAAI.V36I7.20681},
timestamp = {Sat, 16 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/aaai/KirschFHFOC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/SchmittSH22,
author = {Simon Schmitt and
John Shawe{-}Taylor and
Hado van Hasselt},
title = {Chaining Value Functions for Off-Policy Learning},
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 = {8187--8195},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i8.20792},
doi = {10.1609/AAAI.V36I8.20792},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/SchmittSH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/FlennerhagSZHS022,
author = {Sebastian Flennerhag and
Yannick Schroecker and
Tom Zahavy and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Bootstrapped Meta-Learning},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=b-ny3x071E5},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/FlennerhagSZHS022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/SilverGDHH22,
author = {David Silver and
Anirudh Goyal and
Ivo Danihelka and
Matteo Hessel and
Hado van Hasselt},
title = {Learning by Directional Gradient Descent},
booktitle = {The Tenth International Conference on Learning Representations, {ICLR}
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
year = {2022},
url = {https://openreview.net/forum?id=5i7lJLuhTm},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/SilverGDHH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-06468,
author = {Simon Schmitt and
John Shawe{-}Taylor and
Hado van Hasselt},
title = {Chaining Value Functions for Off-Policy Learning},
journal = {CoRR},
volume = {abs/2201.06468},
year = {2022},
url = {https://arxiv.org/abs/2201.06468},
eprinttype = {arXiv},
eprint = {2201.06468},
timestamp = {Fri, 21 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-06468.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-09699,
author = {Veronica Chelu and
Diana Borsa and
Doina Precup and
Hado van Hasselt},
title = {Selective Credit Assignment},
journal = {CoRR},
volume = {abs/2202.09699},
year = {2022},
url = {https://arxiv.org/abs/2202.09699},
eprinttype = {arXiv},
eprint = {2202.09699},
timestamp = {Tue, 01 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-09699.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-07550,
author = {Steven Kapturowski and
V{\'{\i}}ctor Campos and
Ray Jiang and
Nemanja Rakicevic and
Hado van Hasselt and
Charles Blundell and
Adri{\`{a}} Puigdom{\`{e}}nech Badia},
title = {Human-level Atari 200x faster},
journal = {CoRR},
volume = {abs/2209.07550},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.07550},
doi = {10.48550/ARXIV.2209.07550},
eprinttype = {arXiv},
eprint = {2209.07550},
timestamp = {Wed, 02 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-07550.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HasseltMHSBB21,
author = {Hado van Hasselt and
Sephora Madjiheurem and
Matteo Hessel and
David Silver and
Andr{\'{e}} Barreto and
Diana Borsa},
title = {Expected Eligibility Traces},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {9997--10005},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i11.17200},
doi = {10.1609/AAAI.V35I11.17200},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HasseltMHSBB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/GarneloCLTOGHB21,
author = {Marta Garnelo and
Wojciech Marian Czarnecki and
Siqi Liu and
Dhruva Tirumala and
Junhyuk Oh and
Gauthier Gidel and
Hado van Hasselt and
David Balduzzi},
editor = {Frank Dignum and
Alessio Lomuscio and
Ulle Endriss and
Ann Now{\'{e}}},
title = {Pick Your Battles: Interaction Graphs as Population-Level Objectives
for Strategic Diversity},
booktitle = {{AAMAS} '21: 20th International Conference on Autonomous Agents and
Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021},
pages = {1501--1503},
publisher = {{ACM}},
year = {2021},
url = {https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1501.pdf},
doi = {10.5555/3463952.3464139},
timestamp = {Thu, 11 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/GarneloCLTOGHB21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HesselDVGSSWSH21,
author = {Matteo Hessel and
Ivo Danihelka and
Fabio Viola and
Arthur Guez and
Simon Schmitt and
Laurent Sifre and
Theophane Weber and
David Silver and
Hado van Hasselt},
editor = {Marina Meila and
Tong Zhang},
title = {Muesli: Combining Improvements in Policy Optimization},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {4214--4226},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/hessel21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HesselDVGSSWSH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/JiangZXWHBH21,
author = {Ray Jiang and
Tom Zahavy and
Zhongwen Xu and
Adam White and
Matteo Hessel and
Charles Blundell and
Hado van Hasselt},
editor = {Marina Meila and
Tong Zhang},
title = {Emphatic Algorithms for Deep Reinforcement Learning},
booktitle = {Proceedings of the 38th International Conference on Machine Learning,
{ICML} 2021, 18-24 July 2021, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {139},
pages = {5023--5033},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/jiang21j.html},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/JiangZXWHBH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FarquharBMFHHS21,
author = {Gregory Farquhar and
Kate Baumli and
Zita Marinho and
Angelos Filos and
Matteo Hessel and
Hado Philip van Hasselt and
David Silver},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Self-Consistent Models and Values},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {1111--1125},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/08f0efebb1c51aada9430a089a2050cc-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/FarquharBMFHHS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VeeriahZHXOKHSS21,
author = {Vivek Veeriah and
Tom Zahavy and
Matteo Hessel and
Zhongwen Xu and
Junhyuk Oh and
Iurii Kemaev and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Discovery of Options via Meta-Learned Subgoals},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {29861--29873},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/fa246d0262c3925617b0c72bb20eeb1d-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/VeeriahZHXOKHSS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06741,
author = {Vivek Veeriah and
Tom Zahavy and
Matteo Hessel and
Zhongwen Xu and
Junhyuk Oh and
Iurii Kemaev and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Discovery of Options via Meta-Learned Subgoals},
journal = {CoRR},
volume = {abs/2102.06741},
year = {2021},
url = {https://arxiv.org/abs/2102.06741},
eprinttype = {arXiv},
eprint = {2102.06741},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06741.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-12425,
author = {David Raposo and
Samuel Ritter and
Adam Santoro and
Greg Wayne and
Theophane Weber and
Matt M. Botvinick and
Hado van Hasselt and
H. Francis Song},
title = {Synthetic Returns for Long-Term Credit Assignment},
journal = {CoRR},
volume = {abs/2102.12425},
year = {2021},
url = {https://arxiv.org/abs/2102.12425},
eprinttype = {arXiv},
eprint = {2102.12425},
timestamp = {Tue, 02 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-12425.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-06159,
author = {Matteo Hessel and
Ivo Danihelka and
Fabio Viola and
Arthur Guez and
Simon Schmitt and
Laurent Sifre and
Theophane Weber and
David Silver and
Hado van Hasselt},
title = {Muesli: Combining Improvements in Policy Optimization},
journal = {CoRR},
volume = {abs/2104.06159},
year = {2021},
url = {https://arxiv.org/abs/2104.06159},
eprinttype = {arXiv},
eprint = {2104.06159},
timestamp = {Mon, 19 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-06159.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-06272,
author = {Matteo Hessel and
Manuel Kroiss and
Aidan Clark and
Iurii Kemaev and
John Quan and
Thomas Keck and
Fabio Viola and
Hado van Hasselt},
title = {Podracer architectures for scalable Reinforcement Learning},
journal = {CoRR},
volume = {abs/2104.06272},
year = {2021},
url = {https://arxiv.org/abs/2104.06272},
eprinttype = {arXiv},
eprint = {2104.06272},
timestamp = {Mon, 19 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-06272.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2106-11779,
author = {Ray Jiang and
Tom Zahavy and
Zhongwen Xu and
Adam White and
Matteo Hessel and
Charles Blundell and
Hado van Hasselt},
title = {Emphatic Algorithms for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2106.11779},
year = {2021},
url = {https://arxiv.org/abs/2106.11779},
eprinttype = {arXiv},
eprint = {2106.11779},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2106-11779.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-05405,
author = {Ray Jiang and
Shangtong Zhang and
Veronica Chelu and
Adam White and
Hado van Hasselt},
title = {Learning Expected Emphatic Traces for Deep {RL}},
journal = {CoRR},
volume = {abs/2107.05405},
year = {2021},
url = {https://arxiv.org/abs/2107.05405},
eprinttype = {arXiv},
eprint = {2107.05405},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-05405.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-04504,
author = {Sebastian Flennerhag and
Yannick Schroecker and
Tom Zahavy and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Bootstrapped Meta-Learning},
journal = {CoRR},
volume = {abs/2109.04504},
year = {2021},
url = {https://arxiv.org/abs/2109.04504},
eprinttype = {arXiv},
eprint = {2109.04504},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-04504.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10781,
author = {Louis Kirsch and
Sebastian Flennerhag and
Hado van Hasselt and
Abram L. Friesen and
Junhyuk Oh and
Yutian Chen},
title = {Introducing Symmetries to Black Box Meta Reinforcement Learning},
journal = {CoRR},
volume = {abs/2109.10781},
year = {2021},
url = {https://arxiv.org/abs/2109.10781},
eprinttype = {arXiv},
eprint = {2109.10781},
timestamp = {Sat, 16 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-10781.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-04041,
author = {Marta Garnelo and
Wojciech Marian Czarnecki and
Siqi Liu and
Dhruva Tirumala and
Junhyuk Oh and
Gauthier Gidel and
Hado van Hasselt and
David Balduzzi},
title = {Pick Your Battles: Interaction Graphs as Population-Level Objectives
for Strategic Diversity},
journal = {CoRR},
volume = {abs/2110.04041},
year = {2021},
url = {https://arxiv.org/abs/2110.04041},
eprinttype = {arXiv},
eprint = {2110.04041},
timestamp = {Thu, 08 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-04041.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-12840,
author = {Gregory Farquhar and
Kate Baumli and
Zita Marinho and
Angelos Filos and
Matteo Hessel and
Hado van Hasselt and
David Silver},
title = {Self-Consistent Models and Values},
journal = {CoRR},
volume = {abs/2110.12840},
year = {2021},
url = {https://arxiv.org/abs/2110.12840},
eprinttype = {arXiv},
eprint = {2110.12840},
timestamp = {Thu, 28 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-12840.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/RowlandHHBSMD20,
author = {Mark Rowland and
Anna Harutyunyan and
Hado van Hasselt and
Diana Borsa and
Tom Schaul and
R{\'{e}}mi Munos and
Will Dabney},
editor = {Silvia Chiappa and
Roberto Calandra},
title = {Conditional Importance Sampling for Off-Policy Learning},
booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics,
{AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]},
series = {Proceedings of Machine Learning Research},
volume = {108},
pages = {45--55},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v108/rowland20b.html},
timestamp = {Mon, 29 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aistats/RowlandHHBSMD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/OsbandDHASSMLSS20,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
booktitle = {8th International Conference on Learning Representations, {ICLR} 2020,
Addis Ababa, Ethiopia, April 26-30, 2020},
publisher = {OpenReview.net},
year = {2020},
url = {https://openreview.net/forum?id=rygf-kSYwH},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/OsbandDHASSMLSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZhengOHXKHSS20,
author = {Zeyu Zheng and
Junhyuk Oh and
Matteo Hessel and
Zhongwen Xu and
Manuel Kroiss and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {What Can Learned Intrinsic Rewards Capture?},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {11436--11446},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/zheng20b.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZhengOHXKHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/CheluPH20,
author = {Veronica Chelu and
Doina Precup and
Hado van Hasselt},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Forethought and Hindsight in Credit Assignment},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/18064d61b6f93dab8681a460779b8429-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/CheluPH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/OhHCXHSS20,
author = {Junhyuk Oh and
Matteo Hessel and
Wojciech M. Czarnecki and
Zhongwen Xu and
Hado van Hasselt and
Satinder Singh and
David Silver},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Discovering Reinforcement Learning Algorithms},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/0b96d81f0494fde5428c7aea243c9157-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/OhHCXHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuHHOSS20,
author = {Zhongwen Xu and
Hado Philip van Hasselt and
Matteo Hessel and
Junhyuk Oh and
Satinder Singh and
David Silver},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Meta-Gradient Reinforcement Learning with an Objective Discovered
Online},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/ae3d525daf92cee0003a7f2d92c34ea3-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/XuHHOSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZahavyXVHOHSS20,
author = {Tom Zahavy and
Zhongwen Xu and
Vivek Veeriah and
Matteo Hessel and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {A Self-Tuning Actor-Critic Algorithm},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference
on Neural Information Processing Systems 2020, NeurIPS 2020, December
6-12, 2020, virtual},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/f02208a057804ee16ac72ff4d3cec53b-Abstract.html},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZahavyXVHOHSS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-12928,
author = {Tom Zahavy and
Zhongwen Xu and
Vivek Veeriah and
Matteo Hessel and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Self-Tuning Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/2002.12928},
year = {2020},
url = {https://arxiv.org/abs/2002.12928},
eprinttype = {arXiv},
eprint = {2002.12928},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-12928.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-01839,
author = {Hado van Hasselt and
Sephora Madjiheurem and
Matteo Hessel and
David Silver and
Andr{\'{e}} Barreto and
Diana Borsa},
title = {Expected Eligibility Traces},
journal = {CoRR},
volume = {abs/2007.01839},
year = {2020},
url = {https://arxiv.org/abs/2007.01839},
eprinttype = {arXiv},
eprint = {2007.01839},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-01839.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08433,
author = {Zhongwen Xu and
Hado van Hasselt and
Matteo Hessel and
Junhyuk Oh and
Satinder Singh and
David Silver},
title = {Meta-Gradient Reinforcement Learning with an Objective Discovered
Online},
journal = {CoRR},
volume = {abs/2007.08433},
year = {2020},
url = {https://arxiv.org/abs/2007.08433},
eprinttype = {arXiv},
eprint = {2007.08433},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08433.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-08794,
author = {Junhyuk Oh and
Matteo Hessel and
Wojciech M. Czarnecki and
Zhongwen Xu and
Hado van Hasselt and
Satinder Singh and
David Silver},
title = {Discovering Reinforcement Learning Algorithms},
journal = {CoRR},
volume = {abs/2007.08794},
year = {2020},
url = {https://arxiv.org/abs/2007.08794},
eprinttype = {arXiv},
eprint = {2007.08794},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-08794.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-13685,
author = {Veronica Chelu and
Doina Precup and
Hado van Hasselt},
title = {Forethought and Hindsight in Credit Assignment},
journal = {CoRR},
volume = {abs/2010.13685},
year = {2020},
url = {https://arxiv.org/abs/2010.13685},
eprinttype = {arXiv},
eprint = {2010.13685},
timestamp = {Mon, 02 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-13685.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HesselSE0SH19,
author = {Matteo Hessel and
Hubert Soyer and
Lasse Espeholt and
Wojciech Czarnecki and
Simon Schmitt and
Hado van Hasselt},
title = {Multi-Task Deep Reinforcement Learning with PopArt},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {3796--3803},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33013796},
doi = {10.1609/AAAI.V33I01.33013796},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HesselSE0SH19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/BorsaBQMHMSS19,
author = {Diana Borsa and
Andr{\'{e}} Barreto and
John Quan and
Daniel J. Mankowitz and
Hado van Hasselt and
R{\'{e}}mi Munos and
David Silver and
Tom Schaul},
title = {Universal Successor Features Approximators},
booktitle = {7th International Conference on Learning Representations, {ICLR} 2019,
New Orleans, LA, USA, May 6-9, 2019},
publisher = {OpenReview.net},
year = {2019},
url = {https://openreview.net/forum?id=S1VWjiRcKX},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/BorsaBQMHMSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VeeriahHXRLOHSS19,
author = {Vivek Veeriah and
Matteo Hessel and
Zhongwen Xu and
Janarthanan Rajendran and
Richard L. Lewis and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Discovery of Useful Questions as Auxiliary Tasks},
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 = {9306--9317},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/10ff0b5e85e5b85cc3095d431d8c08b4-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/VeeriahHXRLOHSS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HarutyunyanDMAP19,
author = {Anna Harutyunyan and
Will Dabney and
Thomas Mesnard and
Mohammad Gheshlaghi Azar and
Bilal Piot and
Nicolas Heess and
Hado van Hasselt and
Gregory Wayne and
Satinder Singh and
Doina Precup and
R{\'{e}}mi Munos},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Hindsight Credit Assignment},
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 = {12467--12476},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/195f15384c2a79cedf293e4a847ce85c-Abstract.html},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/HarutyunyanDMAP19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HasseltHA19,
author = {Hado van Hasselt and
Matteo Hessel and
John Aslanides},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {When to use parametric models in reinforcement learning?},
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 = {14322--14333},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/1b742ae215adf18b75449c6e272fd92d-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/HasseltHA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-03030,
author = {Pedro A. Ortega and
Jane X. Wang and
Mark Rowland and
Tim Genewein and
Zeb Kurth{-}Nelson and
Razvan Pascanu and
Nicolas Heess and
Joel Veness and
Alexander Pritzel and
Pablo Sprechmann and
Siddhant M. Jayakumar and
Tom McGrath and
Kevin J. Miller and
Mohammad Gheshlaghi Azar and
Ian Osband and
Neil C. Rabinowitz and
Andr{\'{a}}s Gy{\"{o}}rgy and
Silvia Chiappa and
Simon Osindero and
Yee Whye Teh and
Hado van Hasselt and
Nando de Freitas and
Matthew M. Botvinick and
Shane Legg},
title = {Meta-learning of Sequential Strategies},
journal = {CoRR},
volume = {abs/1905.03030},
year = {2019},
url = {http://arxiv.org/abs/1905.03030},
eprinttype = {arXiv},
eprint = {1905.03030},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-03030.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-05243,
author = {Hado van Hasselt and
Matteo Hessel and
John Aslanides},
title = {When to use parametric models in reinforcement learning?},
journal = {CoRR},
volume = {abs/1906.05243},
year = {2019},
url = {http://arxiv.org/abs/1906.05243},
eprinttype = {arXiv},
eprint = {1906.05243},
timestamp = {Fri, 14 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-05243.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-02908,
author = {Matteo Hessel and
Hado van Hasselt and
Joseph Modayil and
David Silver},
title = {On Inductive Biases in Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1907.02908},
year = {2019},
url = {http://arxiv.org/abs/1907.02908},
eprinttype = {arXiv},
eprint = {1907.02908},
timestamp = {Mon, 08 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-02908.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-03687,
author = {Hado van Hasselt and
John Quan and
Matteo Hessel and
Zhongwen Xu and
Diana Borsa and
Andr{\'{e}} Barreto},
title = {General non-linear Bellman equations},
journal = {CoRR},
volume = {abs/1907.03687},
year = {2019},
url = {http://arxiv.org/abs/1907.03687},
eprinttype = {arXiv},
eprint = {1907.03687},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-03687.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-03568,
author = {Ian Osband and
Yotam Doron and
Matteo Hessel and
John Aslanides and
Eren Sezener and
Andre Saraiva and
Katrina McKinney and
Tor Lattimore and
Csaba Szepesv{\'{a}}ri and
Satinder Singh and
Benjamin Van Roy and
Richard S. Sutton and
David Silver and
Hado van Hasselt},
title = {Behaviour Suite for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1908.03568},
year = {2019},
url = {http://arxiv.org/abs/1908.03568},
eprinttype = {arXiv},
eprint = {1908.03568},
timestamp = {Mon, 15 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-03568.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-04607,
author = {Vivek Veeriah and
Matteo Hessel and
Zhongwen Xu and
Richard L. Lewis and
Janarthanan Rajendran and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {Discovery of Useful Questions as Auxiliary Tasks},
journal = {CoRR},
volume = {abs/1909.04607},
year = {2019},
url = {http://arxiv.org/abs/1909.04607},
eprinttype = {arXiv},
eprint = {1909.04607},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-04607.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-07479,
author = {Mark Rowland and
Anna Harutyunyan and
Hado van Hasselt and
Diana Borsa and
Tom Schaul and
R{\'{e}}mi Munos and
Will Dabney},
title = {Conditional Importance Sampling for Off-Policy Learning},
journal = {CoRR},
volume = {abs/1910.07479},
year = {2019},
url = {http://arxiv.org/abs/1910.07479},
eprinttype = {arXiv},
eprint = {1910.07479},
timestamp = {Tue, 22 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-07479.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-02503,
author = {Anna Harutyunyan and
Will Dabney and
Thomas Mesnard and
Mohammad Gheshlaghi Azar and
Bilal Piot and
Nicolas Heess and
Hado van Hasselt and
Greg Wayne and
Satinder Singh and
Doina Precup and
R{\'{e}}mi Munos},
title = {Hindsight Credit Assignment},
journal = {CoRR},
volume = {abs/1912.02503},
year = {2019},
url = {http://arxiv.org/abs/1912.02503},
eprinttype = {arXiv},
eprint = {1912.02503},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-02503.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-05500,
author = {Zeyu Zheng and
Junhyuk Oh and
Matteo Hessel and
Zhongwen Xu and
Manuel Kroiss and
Hado van Hasselt and
David Silver and
Satinder Singh},
title = {What Can Learned Intrinsic Rewards Capture?},
journal = {CoRR},
volume = {abs/1912.05500},
year = {2019},
url = {http://arxiv.org/abs/1912.05500},
eprinttype = {arXiv},
eprint = {1912.05500},
timestamp = {Tue, 19 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-05500.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HesselMHSODHPAS18,
author = {Matteo Hessel and
Joseph Modayil and
Hado van Hasselt and
Tom Schaul and
Georg Ostrovski and
Will Dabney and
Dan Horgan and
Bilal Piot and
Mohammad Gheshlaghi Azar and
David Silver},
editor = {Sheila A. McIlraith and
Kilian Q. Weinberger},
title = {Rainbow: Combining Improvements in Deep Reinforcement Learning},
booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Artificial Intelligence
(IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
2-7, 2018},
pages = {3215--3222},
publisher = {{AAAI} Press},
year = {2018},
url = {https://doi.org/10.1609/aaai.v32i1.11796},
doi = {10.1609/AAAI.V32I1.11796},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HesselMHSODHPAS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HorganQBBHHS18,
author = {Dan Horgan and
John Quan and
David Budden and
Gabriel Barth{-}Maron and
Matteo Hessel and
Hado van Hasselt and
David Silver},
title = {Distributed Prioritized Experience Replay},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=H1Dy---0Z},
timestamp = {Thu, 25 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HorganQBBHHS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BargiacchiVRNH18,
author = {Eugenio Bargiacchi and
Timothy Verstraeten and
Diederik M. Roijers and
Ann Now{\'{e}} and
Hado van Hasselt},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Learning to Coordinate with Coordination Graphs in Repeated Single-Stage
Multi-Agent Decision Problems},
booktitle = {Proceedings of the 35th International Conference on Machine Learning,
{ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July
10-15, 2018},
series = {Proceedings of Machine Learning Research},
volume = {80},
pages = {491--499},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/bargiacchi18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/BargiacchiVRNH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuHS18,
author = {Zhongwen Xu and
Hado van Hasselt and
David Silver},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Meta-Gradient Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {2402--2413},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/2715518c875999308842e3455eda2fe3-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/XuHS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-08294,
author = {Daniel J. Mankowitz and
Augustin Z{\'{\i}}dek and
Andr{\'{e}} Barreto and
Dan Horgan and
Matteo Hessel and
John Quan and
Junhyuk Oh and
Hado van Hasselt and
David Silver and
Tom Schaul},
title = {Unicorn: Continual Learning with a Universal, Off-policy Agent},
journal = {CoRR},
volume = {abs/1802.08294},
year = {2018},
url = {http://arxiv.org/abs/1802.08294},
eprinttype = {arXiv},
eprint = {1802.08294},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-08294.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00933,
author = {Dan Horgan and
John Quan and
David Budden and
Gabriel Barth{-}Maron and
Matteo Hessel and
Hado van Hasselt and
David Silver},
title = {Distributed Prioritized Experience Replay},
journal = {CoRR},
volume = {abs/1803.00933},
year = {2018},
url = {http://arxiv.org/abs/1803.00933},
eprinttype = {arXiv},
eprint = {1803.00933},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-00933.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-09801,
author = {Zhongwen Xu and
Hado van Hasselt and
David Silver},
title = {Meta-Gradient Reinforcement Learning},
journal = {CoRR},
volume = {abs/1805.09801},
year = {2018},
url = {http://arxiv.org/abs/1805.09801},
eprinttype = {arXiv},
eprint = {1805.09801},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-09801.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-11593,
author = {Tobias Pohlen and
Bilal Piot and
Todd Hester and
Mohammad Gheshlaghi Azar and
Dan Horgan and
David Budden and
Gabriel Barth{-}Maron and
Hado van Hasselt and
John Quan and
Mel Vecer{\'{\i}}k and
Matteo Hessel and
R{\'{e}}mi Munos and
Olivier Pietquin},
title = {Observe and Look Further: Achieving Consistent Performance on Atari},
journal = {CoRR},
volume = {abs/1805.11593},
year = {2018},
url = {http://arxiv.org/abs/1805.11593},
eprinttype = {arXiv},
eprint = {1805.11593},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-11593.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-04474,
author = {Matteo Hessel and
Hubert Soyer and
Lasse Espeholt and
Wojciech Czarnecki and
Simon Schmitt and
Hado van Hasselt},
title = {Multi-task Deep Reinforcement Learning with PopArt},
journal = {CoRR},
volume = {abs/1809.04474},
year = {2018},
url = {http://arxiv.org/abs/1809.04474},
eprinttype = {arXiv},
eprint = {1809.04474},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-04474.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-07004,
author = {Tom Schaul and
Hado van Hasselt and
Joseph Modayil and
Martha White and
Adam White and
Pierre{-}Luc Bacon and
Jean Harb and
Shibl Mourad and
Marc G. Bellemare and
Doina Precup},
title = {The Barbados 2018 List of Open Issues in Continual Learning},
journal = {CoRR},
volume = {abs/1811.07004},
year = {2018},
url = {http://arxiv.org/abs/1811.07004},
eprinttype = {arXiv},
eprint = {1811.07004},
timestamp = {Thu, 21 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-07004.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-02648,
author = {Hado van Hasselt and
Yotam Doron and
Florian Strub and
Matteo Hessel and
Nicolas Sonnerat and
Joseph Modayil},
title = {Deep Reinforcement Learning and the Deadly Triad},
journal = {CoRR},
volume = {abs/1812.02648},
year = {2018},
url = {http://arxiv.org/abs/1812.02648},
eprinttype = {arXiv},
eprint = {1812.02648},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-02648.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-07626,
author = {Diana Borsa and
Andr{\'{e}} Barreto and
John Quan and
Daniel J. Mankowitz and
R{\'{e}}mi Munos and
Hado van Hasselt and
David Silver and
Tom Schaul},
title = {Universal Successor Features Approximators},
journal = {CoRR},
volume = {abs/1812.07626},
year = {2018},
url = {http://arxiv.org/abs/1812.07626},
eprinttype = {arXiv},
eprint = {1812.07626},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-07626.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SilverHHSGHDRRB17,
author = {David Silver and
Hado van Hasselt and
Matteo Hessel and
Tom Schaul and
Arthur Guez and
Tim Harley and
Gabriel Dulac{-}Arnold and
David P. Reichert and
Neil C. Rabinowitz and
Andr{\'{e}} Barreto and
Thomas Degris},
editor = {Doina Precup and
Yee Whye Teh},
title = {The Predictron: End-To-End Learning and Planning},
booktitle = {Proceedings of the 34th International Conference on Machine Learning,
{ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017},
series = {Proceedings of Machine Learning Research},
volume = {70},
pages = {3191--3199},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/silver17a.html},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/SilverHHSGHDRRB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuMHBSS17,
author = {Zhongwen Xu and
Joseph Modayil and
Hado van Hasselt and
Andr{\'{e}} Barreto and
David Silver and
Tom Schaul},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Natural Value Approximators: Learning when to Trust Past Estimates},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {2120--2128},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/fb60d411a5c5b72b2e7d3527cfc84fd0-Abstract.html},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/XuMHBSS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BarretoDMHSSH17,
author = {Andr{\'{e}} Barreto and
Will Dabney and
R{\'{e}}mi Munos and
Jonathan J. Hunt and
Tom Schaul and
David Silver and
Hado van Hasselt},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Successor Features for Transfer in Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {4055--4065},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/350db081a661525235354dd3e19b8c05-Abstract.html},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BarretoDMHSSH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-04782,
author = {Oriol Vinyals and
Timo Ewalds and
Sergey Bartunov and
Petko Georgiev and
Alexander Sasha Vezhnevets and
Michelle Yeo and
Alireza Makhzani and
Heinrich K{\"{u}}ttler and
John P. Agapiou and
Julian Schrittwieser and
John Quan and
Stephen Gaffney and
Stig Petersen and
Karen Simonyan and
Tom Schaul and
Hado van Hasselt and
David Silver and
Timothy P. Lillicrap and
Kevin Calderone and
Paul Keet and
Anthony Brunasso and
David Lawrence and
Anders Ekermo and
Jacob Repp and
Rodney Tsing},
title = {StarCraft {II:} {A} New Challenge for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1708.04782},
year = {2017},
url = {http://arxiv.org/abs/1708.04782},
eprinttype = {arXiv},
eprint = {1708.04782},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-04782.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-02298,
author = {Matteo Hessel and
Joseph Modayil and
Hado van Hasselt and
Tom Schaul and
Georg Ostrovski and
Will Dabney and
Daniel Horgan and
Bilal Piot and
Mohammad Gheshlaghi Azar and
David Silver},
title = {Rainbow: Combining Improvements in Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1710.02298},
year = {2017},
url = {http://arxiv.org/abs/1710.02298},
eprinttype = {arXiv},
eprint = {1710.02298},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-02298.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HasseltGS16,
author = {Hado van Hasselt and
Arthur Guez and
David Silver},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Deep Reinforcement Learning with Double Q-Learning},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {2094--2100},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10295},
doi = {10.1609/AAAI.V30I1.10295},
timestamp = {Mon, 04 Sep 2023 15:08:28 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HasseltGS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangSHHLF16,
author = {Ziyu Wang and
Tom Schaul and
Matteo Hessel and
Hado van Hasselt and
Marc Lanctot and
Nando de Freitas},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Dueling Network Architectures for Deep Reinforcement Learning},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {48},
pages = {1995--2003},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/wangf16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/icml/WangSHHLF16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HasseltGHMS16,
author = {Hado van Hasselt and
Arthur Guez and
Matteo Hessel and
Volodymyr Mnih and
David Silver},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Learning values across many orders of magnitude},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {4287--4295},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/5227b6aaf294f5f027273aebf16015f2-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/HasseltGHMS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HasseltGHS16,
author = {Hado van Hasselt and
Arthur Guez and
Matteo Hessel and
David Silver},
title = {Learning functions across many orders of magnitudes},
journal = {CoRR},
volume = {abs/1602.07714},
year = {2016},
url = {http://arxiv.org/abs/1602.07714},
eprinttype = {arXiv},
eprint = {1602.07714},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HasseltGHS16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SilverHHSGHDRRB16,
author = {David Silver and
Hado van Hasselt and
Matteo Hessel and
Tom Schaul and
Arthur Guez and
Tim Harley and
Gabriel Dulac{-}Arnold and
David P. Reichert and
Neil C. Rabinowitz and
Andr{\'{e}} Barreto and
Thomas Degris},
title = {The Predictron: End-To-End Learning and Planning},
journal = {CoRR},
volume = {abs/1612.08810},
year = {2016},
url = {http://arxiv.org/abs/1612.08810},
eprinttype = {arXiv},
eprint = {1612.08810},
timestamp = {Mon, 10 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/SilverHHSGHDRRB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HasseltS15,
author = {Hado van Hasselt and
Richard S. Sutton},
title = {Learning to Predict Independent of Span},
journal = {CoRR},
volume = {abs/1508.04582},
year = {2015},
url = {http://arxiv.org/abs/1508.04582},
eprinttype = {arXiv},
eprint = {1508.04582},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HasseltS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HasseltGS15,
author = {Hado van Hasselt and
Arthur Guez and
David Silver},
title = {Deep Reinforcement Learning with Double Q-learning},
journal = {CoRR},
volume = {abs/1509.06461},
year = {2015},
url = {http://arxiv.org/abs/1509.06461},
eprinttype = {arXiv},
eprint = {1509.06461},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HasseltGS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/SuttonMPH14,
author = {Richard S. Sutton and
Ashique Rupam Mahmood and
Doina Precup and
Hado van Hasselt},
title = {A new Q(lambda) with interim forward view and Monte Carlo equivalence},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {568--576},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/sutton14.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/SuttonMPH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MahmoodHS14,
author = {Ashique Rupam Mahmood and
Hado van Hasselt and
Richard S. Sutton},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Weighted importance sampling for off-policy learning with linear function
approximation},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {3014--3022},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/be53ee61104935234b174e62a07e53cf-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MahmoodHS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/HasseltMS14,
author = {Hado van Hasselt and
Ashique Rupam Mahmood and
Richard S. Sutton},
editor = {Nevin L. Zhang and
Jin Tian},
title = {Off-policy {TD(} l) with a true online equivalence},
booktitle = {Proceedings of the Thirtieth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2014, Quebec City, Quebec, Canada, July 23-27,
2014},
pages = {330--339},
publisher = {{AUAI} Press},
year = {2014},
url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1\&\#38;smnu=2\&\#38;article\_id=2468\&\#38;proceeding\_id=30},
timestamp = {Wed, 03 Feb 2021 11:09:27 +0100},
biburl = {https://dblp.org/rec/conf/uai/HasseltMS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cipls/HasseltP13,
author = {Hado van Hasselt and
Han La Poutr{\'{e}}},
title = {Stacking under uncertainty: We know how to predict, but how should
we act?},
booktitle = {{IEEE} Symposium on Computational Intelligence In Production And Logistics
Systems, {CIPLS} 2013, Singapore, April 16-19, 2013},
pages = {25--32},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/CIPLS.2013.6595196},
doi = {10.1109/CIPLS.2013.6595196},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/cipls/HasseltP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1302-7175,
author = {Hado van Hasselt},
title = {Estimating the Maximum Expected Value: An Analysis of (Nested) Cross
Validation and the Maximum Sample Average},
journal = {CoRR},
volume = {abs/1302.7175},
year = {2013},
url = {http://arxiv.org/abs/1302.7175},
eprinttype = {arXiv},
eprint = {1302.7175},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1302-7175.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/12/Hasselt12,
author = {Hado van Hasselt},
editor = {Marco A. Wiering and
Martijn van Otterlo},
title = {Reinforcement Learning in Continuous State and Action Spaces},
booktitle = {Reinforcement Learning},
series = {Adaptation, Learning, and Optimization},
volume = {12},
pages = {207--251},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-27645-3\_7},
doi = {10.1007/978-3-642-27645-3\_7},
timestamp = {Tue, 29 Dec 2020 18:14:51 +0100},
biburl = {https://dblp.org/rec/books/sp/12/Hasselt12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/basesearch/vanHasselt11,
author = {Hado Philip van Hasselt},
title = {Insights in reinforcement rearning : formal analysis and empirical
evaluation of temporal-difference learning algorithms},
school = {Utrecht University, Netherlands},
year = {2011},
url = {https://dspace.library.uu.nl/handle/1874/192729},
timestamp = {Wed, 24 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/basesearch/vanHasselt11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/SeijenWHW11,
author = {Harm van Seijen and
Shimon Whiteson and
Hado van Hasselt and
Marco A. Wiering},
title = {Exploiting Best-Match Equations for Efficient Reinforcement Learning},
journal = {J. Mach. Learn. Res.},
volume = {12},
pages = {2045--2094},
year = {2011},
url = {https://dl.acm.org/doi/10.5555/1953048.2021066},
doi = {10.5555/1953048.2021066},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/SeijenWHW11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/WieringHPS11,
author = {Marco A. Wiering and
Hado van Hasselt and
Auke{-}Dirk Pietersma and
Lambert Schomaker},
title = {Reinforcement learning algorithms for solving classification problems},
booktitle = {2011 {IEEE} Symposium on Adaptive Dynamic Programming And Reinforcement
Learning, {ADPRL} 2011, Paris, France, April 12-14, 2011},
pages = {91--96},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ADPRL.2011.5967372},
doi = {10.1109/ADPRL.2011.5967372},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/adprl/WieringHPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Hasselt10,
author = {Hado van Hasselt},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Double Q-learning},
booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual
Conference on Neural Information Processing Systems 2010. Proceedings
of a meeting held 6-9 December 2010, Vancouver, British Columbia,
Canada},
pages = {2613--2621},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/091d584fced301b442654dd8c23b3fc9-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/Hasselt10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/WieringH09,
author = {Marco A. Wiering and
Hado van Hasselt},
title = {The {QV} family compared to other reinforcement learning algorithms},
booktitle = {{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement
Learning, {ADPRL} 2009, Nashville, TN, USA, March 31 - April 1, 2009},
pages = {101--108},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ADPRL.2009.4927532},
doi = {10.1109/ADPRL.2009.4927532},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/adprl/WieringH09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/adprl/SeijenHWW09,
author = {Harm van Seijen and
Hado van Hasselt and
Shimon Whiteson and
Marco A. Wiering},
title = {A theoretical and empirical analysis of Expected Sarsa},
booktitle = {{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement
Learning, {ADPRL} 2009, Nashville, TN, USA, March 31 - April 1, 2009},
pages = {177--184},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ADPRL.2009.4927542},
doi = {10.1109/ADPRL.2009.4927542},
timestamp = {Fri, 26 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/adprl/SeijenHWW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ags/WestraHDD09,
author = {Joost Westra and
Hado van Hasselt and
Frank Dignum and
Virginia Dignum},
editor = {Frank Dignum and
Jeffrey M. Bradshaw and
Barry G. Silverman and
Willem A. van Doesburg},
title = {Adaptive Serious Games Using Agent Organizations},
booktitle = {Agents for Games and Simulations, Trends in Techniques, Concepts and
Design {[AGS} 2009, The First International Workshop on Agents for
Games and Simulations, May 11, 2009, Budapest, Hungary]},
series = {Lecture Notes in Computer Science},
volume = {5920},
pages = {206--220},
publisher = {Springer},
year = {2009},
url = {https://doi.org/10.1007/978-3-642-11198-3\_14},
doi = {10.1007/978-3-642-11198-3\_14},
timestamp = {Thu, 28 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ags/WestraHDD09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/HasseltW09,
author = {Hado van Hasselt and
Marco A. Wiering},
title = {Using continuous action spaces to solve discrete problems},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2009, Atlanta,
Georgia, USA, 14-19 June 2009},
pages = {1149--1156},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/IJCNN.2009.5178745},
doi = {10.1109/IJCNN.2009.5178745},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcnn/HasseltW09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsmc/WieringH08,
author = {Marco A. Wiering and
Hado van Hasselt},
title = {Ensemble Algorithms in Reinforcement Learning},
journal = {{IEEE} Trans. Syst. Man Cybern. Part {B}},
volume = {38},
number = {4},
pages = {930--936},
year = {2008},
url = {https://doi.org/10.1109/TSMCB.2008.920231},
doi = {10.1109/TSMCB.2008.920231},
timestamp = {Tue, 29 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tsmc/WieringH08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cig/WestraHDD08,
author = {Joost Westra and
Hado van Hasselt and
Virginia Dignum and
Frank Dignum},
editor = {Philip Hingston and
Luigi Barone},
title = {On-line adapting games using agent organizations},
booktitle = {Proceedings of the 2008 {IEEE} Symposium on Computational Intelligence
and Games, {CIG} 2009, Perth, Australia, 15-18 December, 2008},
pages = {243--250},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/CIG.2008.5035646},
doi = {10.1109/CIG.2008.5035646},
timestamp = {Thu, 28 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cig/WestraHDD08.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 2024-04-25 02:34 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:
