-
2022-10-27: Today we share a paper:
- IN-CONTEXT REINFORCEMENT LEARNING WITH ALGORITHM DISTILLATION, by Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Hansen, Angelos Filos, Ethan Brooks, Maxime Gazeau, Himanshu Sahni, Satinder Singh, Volodymyr Mnih Details
- download link
- keywords: algorithm distillation
- IN-CONTEXT REINFORCEMENT LEARNING WITH ALGORITHM DISTILLATION, by Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Hansen, Angelos Filos, Ethan Brooks, Maxime Gazeau, Himanshu Sahni, Satinder Singh, Volodymyr Mnih Details
-
2022-10-11: Today we share a paper:
- Defining and Characterizing Reward Hacking, by Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, David Krueger Details
- download link
- keywords: reward hacking
- Defining and Characterizing Reward Hacking, by Joar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, David Krueger Details
-
2022-10-07: Today we share a paper:
- How RL Agents Behave When Their Actions Are Modified, by Eric D. Langlois, Tom Everitt Details
- download link
- keywords: modified action
- How RL Agents Behave When Their Actions Are Modified, by Eric D. Langlois, Tom Everitt Details
-
2022-06-19: Today we share a paper:
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations, by Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh Details
- download link
- keywords: offline
- Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations, by Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye Teh Details
-
2021-11-06: Today we share a paper:
- Self-Consistent Models and Values, by Gregory Farquhar, Matteo Hessel, Kate Baumli Zita Marinho, Hado van Hasselt, Angelos Filos, David Silver
- download link
- keywords: model, self-consistent
- Self-Consistent Models and Values, by Gregory Farquhar, Matteo Hessel, Kate Baumli Zita Marinho, Hado van Hasselt, Angelos Filos, David Silver
-
2021-10-22: Today we share a paper:
- An Empirical Investigation of Representation Learning for Imitation, by Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
-
2021-10-20: Today we share a paper:
- Temporal Abstraction in Reinforcement Learning with the Successor Representation, by Marlos C. Machado, André Barreto, Doina Precup
-
2021-10-19: Today we share a paper:
- REPRESENTATION LEARNING VIA INVARIANT CAUSAL MECHANISMS, by Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, Charles Blundell
- download link
- keywords: causal, representation Learning, self-supervised Learning, contrastive Methods, causality
- REPRESENTATION LEARNING VIA INVARIANT CAUSAL MECHANISMS, by Jovana Mitrovic, Brian McWilliams, Jacob Walker, Lars Buesing, Charles Blundell
-
2021-10-16: Today we share a paper:
- Nash Equilibria in Finite-Horizon Multiagent Concurrent Games, by Senthil Rajasekaran, Moshe Y. Vardi
- download link
- keywords: multiagent, Nash, complexity
- Nash Equilibria in Finite-Horizon Multiagent Concurrent Games, by Senthil Rajasekaran, Moshe Y. Vardi
-
2021-10-13: Today we share a paper:
- Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research, by Johan S. Obando-Ceron, Pablo Samuel Castro
- download link
- github repo
- keywords: practice, algorithm, rainbow
- Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research, by Johan S. Obando-Ceron, Pablo Samuel Castro
-
2021-10-11: Today we share a paper:
- Batch size-invariance for policy optimization, by Jacob Hilton, Karl Cobbe, John Schulman
- download link
- keywords: policy, batch-size
- Batch size-invariance for policy optimization, by Jacob Hilton, Karl Cobbe, John Schulman
-
2021-10-08: Today we share a paper;
- Recursively Summarizing Books with Human Feedback, by Jeff Wu, Long Ouyang, Daniel M. Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, Paul Christiano
- download link
- keywords: alignment, summary, gpt-3, language-model
- Recursively Summarizing Books with Human Feedback, by Jeff Wu, Long Ouyang, Daniel M. Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, Paul Christiano
-
2021-10-06: Today we share a paper:
- Reinforcement Learning with Information-Theoretic Actuation, by Elliot Catt, Marcus Hutter, Joel Veness
-
2021-09-28: Today we share a paper:
- Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning, by Yaodong Yang, Jianye Hao, Ben Liao, Kun Shao, Guangyong Chen, Wulong Liu, Hongyao Tang
-
2021-09-24: Today we share a paper:
- A Minimalist Approach to Offline Reinforcement Learning, by Scott Fujimoto, Shixiang Shane Gu
-
2021-09-18: Today we share a paper:
- Negotiating team formation using deep reinforcement learning, by Yoram Bachrach, Richard Everett, Edward Hughes, Angeliki Lazaridou, Joel Z. Leibo, Marc Lanctot, Michael Johanson, Wojciech M. Czarnecki, Thore Graepel
-
2021-09-14: Today we share two papers:
- CoBERL: Contrastive BERT for Reinforcement Learning, by Andrea Banino, Tim Scholtes, Adrià Puidomenech Badia, Jovana Mitrovic, Jacob Walker, Charles Blundell
- Stabilizing Transformers for Reinforcement Learning, by Emilio Parisotto, H. F. Song, Jack W. Rae, Razvan Pascanu, Çaglar Gülçehre, Siddhant M. Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, M. Botvinick, N. Heess, R. Hadsell
-
2021-07-03: Today we share a paper:
- Causally Correct Partial Models for Reinforcement Learning, by Danilo J. Rezende, Ivo Danihelka, George Papamakarios, Nan Rosemary Ke, Ray Jiang, Theophane Weber, Karol Gregor, Hamza Merzic, Fabio Viola, Jane Wang, Jovana Mitrovic, Frederic Besse, Ioannis Antonoglou, Lars Buesing Details
- download link
-
2020-08-02: Today we share a paper:
- Discovering Reinforcement Learning Algorithms, by Junhyuk Oh Matteo Hessel, Wojciech M. Czarnecki, Zhongwen Xu, Hado van Hasselt, Satinder Singh, David Silver Details
- download link
-
2020-07-06: Today we share a paper:
- An operator view of policy gradient methods, by Dibya Ghosh, Marlos C. Machado, and Nicolas Le Roux Details
- download link
-
2020-06-24: Today we share a paper:
- The Value-Improvement Path Towards Better Representations for Reinforcement Learning, by Will Dabney, Andre Barreto, Mark Rowland, Robert Dadashi, John Quan, Marc G. Bellemare, and David Silver Details
- download link
-
2020-06-23: Today we share a paper:
- An Optimistic Perspective on Offline Reinforcement Learning, by Rishabh Agarwal, Dale Schuurmans, and Mohammad Norouzi Details
- download link
-
2020-05-21: Today we share a paper:
- Deterministic Bellman Residual Minimization, by Ehsan Saleh and Nan Jiang Details
- download link
-
2020-05-12: Today we share a paper:
- Plan2Vec: Unsupervised Representation Learning by Latent Plans, by Ge Yang, Amy Zhang, Ari S. Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra Details
- download link
-
2020-05-11: Today we share a paper:
- The Value of Abstraction, by Mark K. Ho, David Abel, Thomas L. Griffiths, Michael L. Littman Details
- download link
-
2020-05-05: Today we share a webconf：
-
2020-04-27: Today we share a paper:
- Behaviour Suite for Reinforcement Learning, by Ian Osband, Yotam Doron, Matteo Hessel, John Aslanides, Eren Sezener, Andre Saraiva, Katrina McKinney, Tor Lattimore, Csaba Szepesvari, Satinder Singh, Benjamin Van Roy, Richard Sutton, David Silver, Hado Van Hasselt Details
- download link
- code repositary
-
2020-04-22: Today we share a webconf:
- RLTheory Seminars: a virtual seminar focuses on theoretical reinforcement learning.
- link
-
2020-04-19: Today we share a paper:
- Artificial and Computational Intelligence in Games: Revolutions in Computational Game AI, by Jialin Liu, Tom Schaul, Pieter Spronck, and Julian Togelius Details
- download link
-
2020-04-13: Today we share a paper:
- Leverage the Average: an Analysis of Regularization in RL, by Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist Details
- download link
-
2020-04-08: Today we share a podcast of Csaba Szepesvari: