Research

Equivariant Networks for Zero-Shot Coordination

Equivariant Networks for Zero-Shot Coordination

Darius Muglich, Christian Schroeder de Witt, Elise van der Pol, Jakob Foerster

NeurIPS 2022

Discovered Policy Optimization

Discovered Policy Optimization

Chris Lu*, Jakub Grudzien Kuba*, Alistair Letcher, Luke Metz, Christian Schroeder de Witt, Jakob Foerster

NeurIPS 2022

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

Minqi Jiang, Michael Dennis, Jack Parker-Holder, Andrei Lupu, Heinrich Kuttler, Edward Grefenstette, Tim Rocktaschel, Jakob Foerster

NeurIPS 2022

Influencing Long-Term Behavior in Multi-Agent Reinforcement Learning

Influencing Long-Term Behavior in Multi-Agent Reinforcement Learning

Dong-Ki Kim, Matthew Reimer, Miao Liu, Jakob Foerster, Michael Everett, Chuangchuang Sun, Gerald Tesauro, Jonathan How

NeurIPS 2022

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

Eugene Vinitsky, Nathan Lichtlé, Xiaomeng Yang, Brandon Amos, Jakob Foerster

NeurIPS Datasets and Benchmarks 2022

Proximal Learning with Opponent-Learning Awareness

Proximal Learning with Opponent-Learning Awareness

Stephen Zhao, Chris Lu, Roger Baker Grosse, Jakob Foerster

NeurIPS 2022

Self-Explaining Deviations for Coordination

Self-Explaining Deviations for Coordination

Hengyuan Hu, Samuel Sokota, David Wu, Anton Bakhtin, Andrei Lupu, Brandon Cui, Jakob Foerster

NeurIPS 2022

Model-Free Opponent Shaping

Model-Free Opponent Shaping

Chris Lu, Timon Willi, Christian Schroeder de Witt, Jakob Foerster

ICML 2022 (Spotlight)

Communicating via Markov Decision Processes

Communicating via Markov Decision Processes

Samuel Sokota*, Christian Schroeder de Witt*, Maximilian Igl, Luisa M Zintgraf, Philip Torr, J. Zico Kolter, Shimon Whiteson, Jakob Foerster

ICML 2022 (Spotlight)

Generalized Beliefs for Cooperative AI

Generalized Beliefs for Cooperative AI

Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt, Shimon Whiteson, Jakob Foerster

ICML 2022 (Spotlight)

Mirror Learning: A Unifying Framework of Policy Optimisation

Mirror Learning: A Unifying Framework of Policy Optimisation

Jakub Grudzien Kuba, Christian Schroeder de Witt, Jakob Foerster

ICML 2022 (Spotlight)

COLA: Consistent Learning with Opponent-Learning Awareness

COLA: Consistent Learning with Opponent-Learning Awareness

Timon Willi*, Johannes Treutlein*, Alistair Letcher*, Jakob Foerster

ICML 2022 (Spotlight)