7 papers
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
Maksymilian Wolski, Nicholas Hoernle, Johannes Forkel +1
AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot coordination (ZSC) algorithms…
Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
Clarisse Wibault, Johannes Forkel, Sebastian Towers +9
Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has been limited since model-free metho…
High entropy leads to symmetry-equivariant policies in Dec-POMDPs
Johannes Forkel, Constantin Ruhdorfer, Michael Beukman +2
We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initia…
Ad-Hoc Human-AI Coordination Challenge
Tin Dizdarević, Ravi Hammond, Tobias Gessler +7
Achieving seamless coordination between AI agents and humans is crucial for real-world applications, yet it remains a significant open challenge. Hanabi is a cooperative card game…
Fully Offline Reinforcement Learning
Mattie Fellows, Clarisse Wibault, Uljad Berdica +3
Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offli…
Expected Return Symmetries
Darius Muglich, Johannes Forkel, Elise van der Pol +1
Symmetry is an important inductive bias that can improve model robustness and generalization across many deep learning domains. In multi-agent settings, a priori known symmetries h…