Sotabase

Career

· Senior Tech Lead, Multi-Agent Universal Intelligence Team, Meta (formerly Facebook)2024–
· Research Scientist and Associate Professor, University of Oxford, Department of Engineering Science2021–
· Research Scientist, Facebook AI Research (FAIR)2018–
· Research Intern, Google Brain (Internship)2017–
· Research Intern, OpenAI (Internship)2017–
· Research Intern, Google (Internship)2016–

Publications (79)

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Journal of machine learning research · 2020
1,190
cited
"Other-Play" for Zero-Shot Coordination
International Conference on Machine Learning · 2020
258
cited
Evolving Curricula with Regret-Based Environment Design
International Conference on Machine Learning · 2022
166
cited
Trajectory Diversity for Zero-Shot Coordination
Adaptive Agents and Multi-Agent Systems · 2021
149
cited
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Neural Information Processing Systems · 2022
136
cited
Structured State Space Models for In-Context Reinforcement Learning
Neural Information Processing Systems · 2023
131
cited
Replay-Guided Adversarial Environment Design
Neural Information Processing Systems · 2021
130
cited
Discovered Policy Optimisation
Neural Information Processing Systems · 2022
109
cited
Multi-Agent Risks from Advanced AI
arXiv.org · 2025
88
cited
Off-Belief Learning
International Conference on Machine Learning · 2021
82
cited
Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
Neural Information Processing Systems · 2022
65
cited
COLA: Consistent Learning with Opponent-Learning Awareness
International Conference on Machine Learning · 2022
59
cited
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Adaptive Agents and Multi-Agent Systems · 2023
54
cited
Model-Free Opponent Shaping
International Conference on Machine Learning · 2022
51
cited
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
arXiv.org · 2025
47
cited
Perfectly Secure Steganography Using Minimum Entropy Coupling
International Conference on Learning Representations · 2022
47
cited
A New Formalism, Method and Open Issues for Zero-Shot Coordination
International Conference on Machine Learning · 2021
42
cited
K-level Reasoning for Zero-Shot Coordination in Hanabi
Neural Information Processing Systems · 2022
40
cited
JaxMARL: Multi-Agent RL Environments in JAX
arXiv.org · 2023
38
cited
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
International Conference on Learning Representations · 2023
36
cited
Sotabase
Jakob Foerster | Researcher Profile | Sotabase | Sotabase