default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Arthur Guez
@article{DBLP:journals/corr/abs-2406-02035,
author = {Khimya Khetarpal and
Zhaohan Daniel Guo and
Bernardo {\'{A}}vila Pires and
Yunhao Tang and
Clare Lyle and
Mark Rowland and
Nicolas Heess and
Diana Borsa and
Arthur Guez and
Will Dabney},
title = {A Unifying Framework for Action-Conditional Self-Predictive Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2406.02035},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2406.02035},
doi = {10.48550/ARXIV.2406.02035},
eprinttype = {arXiv},
eprint = {2406.02035},
timestamp = {Thu, 04 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2406-02035.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-10587,
author = {Veronica Chelu and
Tom Zahavy and
Arthur Guez and
Doina Precup and
Sebastian Flennerhag},
title = {Optimism and Adaptivity in Policy Optimization},
journal = {CoRR},
volume = {abs/2306.10587},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.10587},
doi = {10.48550/ARXIV.2306.10587},
eprinttype = {arXiv},
eprint = {2306.10587},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-10587.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/0004PMHPKG22,
author = {Jongmin Lee and
Cosmin Paduraru and
Daniel J. Mankowitz and
Nicolas Heess and
Doina Precup and
Kee{-}Eung Kim and
Arthur Guez},
title = {COptiDICE: Offline Constrained Reinforcement Learning via Stationary
Distribution Correction Estimation},
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=FLA55mBee6Q},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/0004PMHPKG22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/DanihelkaGSS22,
author = {Ivo Danihelka and
Arthur Guez and
Julian Schrittwieser and
David Silver},
title = {Policy improvement by planning with Gumbel},
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=bERaNdoegnO},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/DanihelkaGSS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GoyalFBWKBGMHKV22,
author = {Anirudh Goyal and
Abram L. Friesen and
Andrea Banino and
Theophane Weber and
Nan Rosemary Ke and
Adri{\`{a}} Puigdom{\`{e}}nech Badia and
Arthur Guez and
Mehdi Mirza and
Peter Conway Humphreys and
Ksenia Konyushkova and
Michal Valko and
Simon Osindero and
Timothy P. Lillicrap and
Nicolas Heess and
Charles Blundell},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Retrieval-Augmented Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {7740--7765},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/goyal22a.html},
timestamp = {Sun, 12 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/GoyalFBWKBGMHKV22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HumphreysGTSWL22,
author = {Peter Conway Humphreys and
Arthur Guez and
Olivier Tieleman and
Laurent Sifre and
Theophane Weber and
Timothy P. Lillicrap},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Large-Scale Retrieval for Reinforcement Learning},
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/7eca17ef54789b0663cab421f2e9dbf5-Abstract-Conference.html},
timestamp = {Sun, 12 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/HumphreysGTSWL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-08417,
author = {Anirudh Goyal and
Abram L. Friesen and
Andrea Banino and
Theophane Weber and
Nan Rosemary Ke and
Adri{\`{a}} Puigdom{\`{e}}nech Badia and
Arthur Guez and
Mehdi Mirza and
Ksenia Konyushkova and
Michal Valko and
Simon Osindero and
Timothy P. Lillicrap and
Nicolas Heess and
Charles Blundell},
title = {Retrieval-Augmented Reinforcement Learning},
journal = {CoRR},
volume = {abs/2202.08417},
year = {2022},
url = {https://arxiv.org/abs/2202.08417},
eprinttype = {arXiv},
eprint = {2202.08417},
timestamp = {Tue, 01 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-08417.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-08957,
author = {Jongmin Lee and
Cosmin Paduraru and
Daniel J. Mankowitz and
Nicolas Heess and
Doina Precup and
Kee{-}Eung Kim and
Arthur Guez},
title = {COptiDICE: Offline Constrained Reinforcement Learning via Stationary
Distribution Correction Estimation},
journal = {CoRR},
volume = {abs/2204.08957},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.08957},
doi = {10.48550/ARXIV.2204.08957},
eprinttype = {arXiv},
eprint = {2204.08957},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-08957.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-05314,
author = {Peter Conway Humphreys and
Arthur Guez and
Olivier Tieleman and
Laurent Sifre and
Th{\'{e}}ophane Weber and
Timothy P. Lillicrap},
title = {Large-Scale Retrieval for Reinforcement Learning},
journal = {CoRR},
volume = {abs/2206.05314},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.05314},
doi = {10.48550/ARXIV.2206.05314},
eprinttype = {arXiv},
eprint = {2206.05314},
timestamp = {Sun, 12 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-05314.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HamrickFBGVWABV21,
author = {Jessica B. Hamrick and
Abram L. Friesen and
Feryal M. P. Behbahani and
Arthur Guez and
Fabio Viola and
Sims Witherspoon and
Thomas Anthony and
Lars Holger Buesing and
Petar Velickovic and
Theophane Weber},
title = {On the role of planning in model-based deep reinforcement learning},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=IrM64DGB21},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/HamrickFBGVWABV21.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/MesnardWVTSHDSH21,
author = {Thomas Mesnard and
Theophane Weber and
Fabio Viola and
Shantanu Thakoor and
Alaa Saade and
Anna Harutyunyan and
Will Dabney and
Thomas S. Stepleton and
Nicolas Heess and
Arthur Guez and
Eric Moulines and
Marcus Hutter and
Lars Buesing and
R{\'{e}}mi Munos},
editor = {Marina Meila and
Tong Zhang},
title = {Counterfactual Credit Assignment in Model-Free 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 = {7654--7664},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/mesnard21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MesnardWVTSHDSH21.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/nature/SchrittwieserAH20,
author = {Julian Schrittwieser and
Ioannis Antonoglou and
Thomas Hubert and
Karen Simonyan and
Laurent Sifre and
Simon Schmitt and
Arthur Guez and
Edward Lockhart and
Demis Hassabis and
Thore Graepel and
Timothy P. Lillicrap and
David Silver},
title = {Mastering Atari, Go, chess and shogi by planning with a learned model},
journal = {Nat.},
volume = {588},
number = {7839},
pages = {604--609},
year = {2020},
url = {https://doi.org/10.1038/s41586-020-03051-4},
doi = {10.1038/S41586-020-03051-4},
timestamp = {Fri, 02 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/SchrittwieserAH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuezVWBKPSH20,
author = {Arthur Guez and
Fabio Viola and
Theophane Weber and
Lars Buesing and
Steven Kapturowski and
Doina Precup and
David Silver and
Nicolas Heess},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Value-driven Hindsight Modelling},
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/9381fc93ad66f9ec4b2eef71147a6665-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GuezVWBKPSH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-08329,
author = {Arthur Guez and
Fabio Viola and
Th{\'{e}}ophane Weber and
Lars Buesing and
Steven Kapturowski and
Doina Precup and
David Silver and
Nicolas Heess},
title = {Value-driven Hindsight Modelling},
journal = {CoRR},
volume = {abs/2002.08329},
year = {2020},
url = {https://arxiv.org/abs/2002.08329},
eprinttype = {arXiv},
eprint = {2002.08329},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-08329.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2009-05524,
author = {Mehdi Mirza and
Andrew Jaegle and
Jonathan J. Hunt and
Arthur Guez and
Saran Tunyasuvunakool and
Alistair Muldal and
Th{\'{e}}ophane Weber and
P{\'{e}}ter Karkus and
S{\'{e}}bastien Racani{\`{e}}re and
Lars Buesing and
Timothy P. Lillicrap and
Nicolas Heess},
title = {Physically Embedded Planning Problems: New Challenges for Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2009.05524},
year = {2020},
url = {https://arxiv.org/abs/2009.05524},
eprinttype = {arXiv},
eprint = {2009.05524},
timestamp = {Thu, 17 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2009-05524.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-01298,
author = {P{\'{e}}ter Karkus and
Mehdi Mirza and
Arthur Guez and
Andrew Jaegle and
Timothy P. Lillicrap and
Lars Buesing and
Nicolas Heess and
Theophane Weber},
title = {Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for
Physically Embedded 3D Sokoban},
journal = {CoRR},
volume = {abs/2010.01298},
year = {2020},
url = {https://arxiv.org/abs/2010.01298},
eprinttype = {arXiv},
eprint = {2010.01298},
timestamp = {Mon, 12 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-01298.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-04021,
author = {Jessica B. Hamrick and
Abram L. Friesen and
Feryal M. P. Behbahani and
Arthur Guez and
Fabio Viola and
Sims Witherspoon and
Thomas Anthony and
Lars Buesing and
Petar Velickovic and
Th{\'{e}}ophane Weber},
title = {On the role of planning in model-based deep reinforcement learning},
journal = {CoRR},
volume = {abs/2011.04021},
year = {2020},
url = {https://arxiv.org/abs/2011.04021},
eprinttype = {arXiv},
eprint = {2011.04021},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-04021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-09464,
author = {Thomas Mesnard and
Th{\'{e}}ophane Weber and
Fabio Viola and
Shantanu Thakoor and
Alaa Saade and
Anna Harutyunyan and
Will Dabney and
Tom Stepleton and
Nicolas Heess and
Arthur Guez and
Marcus Hutter and
Lars Buesing and
R{\'{e}}mi Munos},
title = {Counterfactual Credit Assignment in Model-Free Reinforcement Learning},
journal = {CoRR},
volume = {abs/2011.09464},
year = {2020},
url = {https://arxiv.org/abs/2011.09464},
eprinttype = {arXiv},
eprint = {2011.09464},
timestamp = {Wed, 25 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-09464.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/BuesingWZHRGL19,
author = {Lars Buesing and
Theophane Weber and
Yori Zwols and
Nicolas Heess and
S{\'{e}}bastien Racani{\`{e}}re and
Arthur Guez and
Jean{-}Baptiste Lespiau},
title = {Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search},
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=BJG0voC9YQ},
timestamp = {Thu, 25 Jul 2019 13:03:15 +0200},
biburl = {https://dblp.org/rec/conf/iclr/BuesingWZHRGL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GuezMGKRWRSOEWS19,
author = {Arthur Guez and
Mehdi Mirza and
Karol Gregor and
Rishabh Kabra and
S{\'{e}}bastien Racani{\`{e}}re and
Theophane Weber and
David Raposo and
Adam Santoro and
Laurent Orseau and
Tom Eccles and
Greg Wayne and
David Silver and
Timothy P. Lillicrap},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {An Investigation of Model-Free Planning},
booktitle = {Proceedings of the 36th International Conference on Machine Learning,
{ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {97},
pages = {2464--2473},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/guez19a.html},
timestamp = {Tue, 11 Jun 2019 15:37:38 +0200},
biburl = {https://dblp.org/rec/conf/icml/GuezMGKRWRSOEWS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-03559,
author = {Arthur Guez and
Mehdi Mirza and
Karol Gregor and
Rishabh Kabra and
S{\'{e}}bastien Racani{\`{e}}re and
Th{\'{e}}ophane Weber and
David Raposo and
Adam Santoro and
Laurent Orseau and
Tom Eccles and
Greg Wayne and
David Silver and
Timothy P. Lillicrap},
title = {An investigation of model-free planning},
journal = {CoRR},
volume = {abs/1901.03559},
year = {2019},
url = {http://arxiv.org/abs/1901.03559},
eprinttype = {arXiv},
eprint = {1901.03559},
timestamp = {Fri, 01 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-03559.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-00528,
author = {Shruti Mishra and
Abbas Abdolmaleki and
Arthur Guez and
Piotr Trochim and
Doina Precup},
title = {Augmenting learning using symmetry in a biologically-inspired domain},
journal = {CoRR},
volume = {abs/1910.00528},
year = {2019},
url = {http://arxiv.org/abs/1910.00528},
eprinttype = {arXiv},
eprint = {1910.00528},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-00528.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-08265,
author = {Julian Schrittwieser and
Ioannis Antonoglou and
Thomas Hubert and
Karen Simonyan and
Laurent Sifre and
Simon Schmitt and
Arthur Guez and
Edward Lockhart and
Demis Hassabis and
Thore Graepel and
Timothy P. Lillicrap and
David Silver},
title = {Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model},
journal = {CoRR},
volume = {abs/1911.08265},
year = {2019},
url = {http://arxiv.org/abs/1911.08265},
eprinttype = {arXiv},
eprint = {1911.08265},
timestamp = {Mon, 02 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-08265.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cogsci/KruscheSGS18,
author = {Moritz Krusche and
Eric Schulz and
Arthur Guez and
Maarten Speekenbrink},
editor = {Chuck Kalish and
Martina A. Rau and
Xiaojin (Jerry) Zhu and
Timothy T. Rogers},
title = {Adaptive planning in human search},
booktitle = {Proceedings of the 40th Annual Meeting of the Cognitive Science Society,
CogSci 2018, Madison, WI, USA, July 25-28, 2018},
publisher = {cognitivesciencesociety.org},
year = {2018},
url = {https://mindmodeling.org/cogsci2018/papers/0379/index.html},
timestamp = {Wed, 17 Apr 2024 12:43:20 +0200},
biburl = {https://dblp.org/rec/conf/cogsci/KruscheSGS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GuezWASVWMS18,
author = {Arthur Guez and
Theophane Weber and
Ioannis Antonoglou and
Karen Simonyan and
Oriol Vinyals and
Daan Wierstra and
R{\'{e}}mi Munos and
David Silver},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Learning to Search with MCTSnets},
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 = {1817--1826},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/guez18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/GuezWASVWMS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-04697,
author = {Arthur Guez and
Th{\'{e}}ophane Weber and
Ioannis Antonoglou and
Karen Simonyan and
Oriol Vinyals and
Daan Wierstra and
R{\'{e}}mi Munos and
David Silver},
title = {Learning to Search with MCTSnets},
journal = {CoRR},
volume = {abs/1802.04697},
year = {2018},
url = {http://arxiv.org/abs/1802.04697},
eprinttype = {arXiv},
eprint = {1802.04697},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-04697.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-06272,
author = {Lars Buesing and
Theophane Weber and
Yori Zwols and
S{\'{e}}bastien Racani{\`{e}}re and
Arthur Guez and
Jean{-}Baptiste Lespiau and
Nicolas Heess},
title = {Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search},
journal = {CoRR},
volume = {abs/1811.06272},
year = {2018},
url = {http://arxiv.org/abs/1811.06272},
eprinttype = {arXiv},
eprint = {1811.06272},
timestamp = {Sun, 25 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-06272.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/SilverSSAHGHBLB17,
author = {David Silver and
Julian Schrittwieser and
Karen Simonyan and
Ioannis Antonoglou and
Aja Huang and
Arthur Guez and
Thomas Hubert and
Lucas Baker and
Matthew Lai and
Adrian Bolton and
Yutian Chen and
Timothy P. Lillicrap and
Fan Hui and
Laurent Sifre and
George van den Driessche and
Thore Graepel and
Demis Hassabis},
title = {Mastering the game of Go without human knowledge},
journal = {Nat.},
volume = {550},
number = {7676},
pages = {354--359},
year = {2017},
url = {https://doi.org/10.1038/nature24270},
doi = {10.1038/NATURE24270},
timestamp = {Mon, 22 Jul 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/SilverSSAHGHBLB17.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/RacaniereWRBGRB17,
author = {S{\'{e}}bastien Racani{\`{e}}re and
Theophane Weber and
David P. Reichert and
Lars Buesing and
Arthur Guez and
Danilo Jimenez Rezende and
Adri{\`{a}} Puigdom{\`{e}}nech Badia and
Oriol Vinyals and
Nicolas Heess and
Yujia Li and
Razvan Pascanu and
Peter W. Battaglia and
Demis Hassabis and
David Silver and
Daan Wierstra},
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 = {Imagination-Augmented Agents for Deep 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 = {5690--5701},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/9e82757e9a1c12cb710ad680db11f6f1-Abstract.html},
timestamp = {Sat, 02 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/RacaniereWRBGRB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WeberRRBGRBVHLP17,
author = {Theophane Weber and
S{\'{e}}bastien Racani{\`{e}}re and
David P. Reichert and
Lars Buesing and
Arthur Guez and
Danilo Jimenez Rezende and
Adri{\`{a}} Puigdom{\`{e}}nech Badia and
Oriol Vinyals and
Nicolas Heess and
Yujia Li and
Razvan Pascanu and
Peter W. Battaglia and
David Silver and
Daan Wierstra},
title = {Imagination-Augmented Agents for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1707.06203},
year = {2017},
url = {http://arxiv.org/abs/1707.06203},
eprinttype = {arXiv},
eprint = {1707.06203},
timestamp = {Sat, 02 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/WeberRRBGRBVHLP17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-01815,
author = {David Silver and
Thomas Hubert and
Julian Schrittwieser and
Ioannis Antonoglou and
Matthew Lai and
Arthur Guez and
Marc Lanctot and
Laurent Sifre and
Dharshan Kumaran and
Thore Graepel and
Timothy P. Lillicrap and
Karen Simonyan and
Demis Hassabis},
title = {Mastering Chess and Shogi by Self-Play with a General Reinforcement
Learning Algorithm},
journal = {CoRR},
volume = {abs/1712.01815},
year = {2017},
url = {http://arxiv.org/abs/1712.01815},
eprinttype = {arXiv},
eprint = {1712.01815},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1712-01815.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/nature/SilverHMGSDSAPL16,
author = {David Silver and
Aja Huang and
Chris J. Maddison and
Arthur Guez and
Laurent Sifre and
George van den Driessche and
Julian Schrittwieser and
Ioannis Antonoglou and
Vedavyas Panneershelvam and
Marc Lanctot and
Sander Dieleman and
Dominik Grewe and
John Nham and
Nal Kalchbrenner and
Ilya Sutskever and
Timothy P. Lillicrap and
Madeleine Leach and
Koray Kavukcuoglu and
Thore Graepel and
Demis Hassabis},
title = {Mastering the game of Go with deep neural networks and tree search},
journal = {Nat.},
volume = {529},
number = {7587},
pages = {484--489},
year = {2016},
url = {https://doi.org/10.1038/nature16961},
doi = {10.1038/NATURE16961},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/nature/SilverHMGSDSAPL16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/BellemareOGTM16,
author = {Marc G. Bellemare and
Georg Ostrovski and
Arthur Guez and
Philip S. Thomas and
R{\'{e}}mi Munos},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Increasing the Action Gap: New Operators for Reinforcement Learning},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {1476--1483},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10303},
doi = {10.1609/AAAI.V30I1.10303},
timestamp = {Mon, 04 Sep 2023 15:08:28 +0200},
biburl = {https://dblp.org/rec/conf/aaai/BellemareOGTM16.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 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HasseltGS16.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/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}
}
@article{DBLP:journals/corr/BellemareOGTM15,
author = {Marc G. Bellemare and
Georg Ostrovski and
Arthur Guez and
Philip S. Thomas and
R{\'{e}}mi Munos},
title = {Increasing the Action Gap: New Operators for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1512.04860},
year = {2015},
url = {http://arxiv.org/abs/1512.04860},
eprinttype = {arXiv},
eprint = {1512.04860},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/BellemareOGTM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuezHSD14,
author = {Arthur Guez and
Nicolas Heess and
David Silver and
Peter Dayan},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Bayes-Adaptive Simulation-based Search with Value 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 = {451--459},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/839ab46820b524afda05122893c2fe8e-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuezHSD14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GuezSD14,
author = {Arthur Guez and
David Silver and
Peter Dayan},
title = {Better Optimism By Bayes: Adaptive Planning with Rich Models},
journal = {CoRR},
volume = {abs/1402.1958},
year = {2014},
url = {http://arxiv.org/abs/1402.1958},
eprinttype = {arXiv},
eprint = {1402.1958},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GuezSD14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/GuezSD13,
author = {Arthur Guez and
David Silver and
Peter Dayan},
title = {Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based
on Monte-Carlo Tree Search},
journal = {J. Artif. Intell. Res.},
volume = {48},
pages = {841--883},
year = {2013},
url = {https://doi.org/10.1613/jair.4117},
doi = {10.1613/JAIR.4117},
timestamp = {Mon, 21 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jair/GuezSD13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GuezSD12,
author = {Arthur Guez and
David Silver and
Peter Dayan},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based
Search},
booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual
Conference on Neural Information Processing Systems 2012. Proceedings
of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States},
pages = {1034--1042},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/35051070e572e47d2c26c241ab88307f-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/GuezSD12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-3109,
author = {Arthur Guez and
David Silver and
Peter Dayan},
title = {Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based
Search},
journal = {CoRR},
volume = {abs/1205.3109},
year = {2012},
url = {http://arxiv.org/abs/1205.3109},
eprinttype = {arXiv},
eprint = {1205.3109},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-3109.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icra/GuezP10,
author = {Arthur Guez and
Joelle Pineau},
title = {Multi-tasking {SLAM}},
booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA}
2010, Anchorage, Alaska, USA, 3-7 May 2010},
pages = {377--384},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ROBOT.2010.5509969},
doi = {10.1109/ROBOT.2010.5509969},
timestamp = {Mon, 22 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icra/GuezP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijns/PineauGVPA09,
author = {Joelle Pineau and
Arthur Guez and
Robert D. Vincent and
Gabriella Panuccio and
Massimo Avoli},
title = {Treating Epilepsy via Adaptive Neurostimulation: a Reinforcement Learning
Approach},
journal = {Int. J. Neural Syst.},
volume = {19},
number = {4},
pages = {227--240},
year = {2009},
url = {https://doi.org/10.1142/S0129065709001987},
doi = {10.1142/S0129065709001987},
timestamp = {Wed, 14 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijns/PineauGVPA09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/GuezVAP08,
author = {Arthur Guez and
Robert D. Vincent and
Massimo Avoli and
Joelle Pineau},
editor = {Dieter Fox and
Carla P. Gomes},
title = {Adaptive Treatment of Epilepsy via Batch-mode Reinforcement Learning},
booktitle = {Proceedings of the Twenty-Third {AAAI} Conference on Artificial Intelligence,
{AAAI} 2008, Chicago, Illinois, USA, July 13-17, 2008},
pages = {1671--1678},
publisher = {{AAAI} Press},
year = {2008},
url = {http://www.aaai.org/Library/IAAI/2008/iaai08-008.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/GuezVAP08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
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 2024-07-23 21:57 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:
