Research

Discovering Temporally-Aware Reinforcement Learning Algorithms

Discovering Temporally-Aware Reinforcement Learning Algorithms

Matthew Jackson*, Chris Lu*, Louis Kirsch, Robert Lange, Shimon Whiteson, Jakob Foerster

ICLR 2024

Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Tim Franzmeyer, Stephen McAleer, Joao Henriques, Jakob Foerster, Philip Torr, Adel Bibi, Christian Schroeder de Witt

ICLR 2024

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Matthew Jackson, Minqi Jiang, Jack Parker-Holder, Risto Vuorio, Chris Lu, Greg Farquhar, Shimon Whiteson, Jakob Foerster

NeurIPS 2023

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

Benjamin Ellis, Jonathan Cook, Skander Moalla, Mikayel Samvelyan, Mingfei Sun, Anuj Mahajan, Jakob Foerster, Shimon Whiteson

NeurIPS Datasets and Benchmarks 2023

Structured State Space Models for In-Context Reinforcement Learning

Structured State Space Models for In-Context Reinforcement Learning

Chris Lu, Yannick Schroecker, Albert Gu, Emilio Parisotto, Jakob Foerster, Satinder Singh, Feryal Behbahani

NeurIPS 2023

Generative AI for End-to-End Limit Order Book Modelling

Generative AI for End-to-End Limit Order Book Modelling

Peer Nagy, Sascha Frey, Silvia Sapora, Kang Li, Anisoara Calinescu, Stefan Zohren, Jakob Foerster

ICAIF 2023

JAX-LOB: A GPU-Accelerated Limit Order Book Simulator to Unlock Large-Scale RL for Trading

JAX-LOB: A GPU-Accelerated Limit Order Book Simulator to Unlock Large-Scale RL for Trading

Sascha Frey*, Kang Li*, Peer Nagy*, Silvia Sapora, Chris Lu, Stefan Zohren, Jakob Foerster, Anisoara Calinescu

ICAIF 2023 (Best Academic Paper Award)

Adversarial Cheap Talk

Adversarial Cheap Talk

Chris Lu, Timon Willi, Alistair Letcher, Jakob Foerster

ICML 2023

Perfectly Secure Steganography using Minimum Entropy Coupling

Perfectly Secure Steganography using Minimum Entropy Coupling

Christian Schroeder de Witt*, Samuel Sokota*, Ziko Kolter, Jakob Foerster, Martin Strohmeier

ICLR 2023

Adversarial Diversity for Hanabi

Adversarial Diversity for Hanabi

Brandon Cui*, Andrei Lupu*, Samuel Sokota, Hengyuan Hu, David J Wu, Jakob Foerster

ICLR 2023

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

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

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

Off-Team Learning

Off-Team Learning

Brandon Cui, Hengyuan Hu, Samuel Sokota, Andrei Lupu, Jakob Foerster

NeurIPS 2022

Proximal Learning with Opponent-Learning Awareness

Proximal Learning with Opponent-Learning Awareness

Stephen Zhao, Chris Lu, Roger Baker Grosse, 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

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)