On The Impossibility Of Learning To Cooperate With Adaptive Partner Strategies In Repeated Games

Abstract

Learning to cooperate with other agents is challenging when those agents also possess the ability to adapt to our own behavior. Practical and theoretical approaches to learning in cooperative settings typically assume that other agents' behaviors are stationary, or else make very specific assumptions about other agents' learning processes. The goal of this work is to understand whether we can reliably learn to cooperate with other agents without such restrictive assumptions, which are unlikely to hold in real-world applications. Our main contribution is a set of impossibility results, which show that no learning algorithm can reliably learn to cooperate with all possible adaptive partners in a repeated matrix game, even if that partner is guaranteed to cooperate with some stationary strategy. Motivated by these results, we then discuss potential alternative assumptions which capture the idea that an adaptive partner will only adapt rationally to our behavior.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyloftin2022on

Related papers

• The Price Of Paranoia: Robust Risk-sensitive Cooperation In Non-stationary Multi-agent Reinforcement Learning (2026)0.00
• Interactive Inverse Reinforcement Learning For Cooperative Games (2021)0.00
• Loss Aversion Fosters Coordination Among Independent Reinforcement Learners (2019)0.00
• Behavioral Differences Is The Key Of Ad-hoc Team Cooperation In Multiplayer Games Hanabi (2023)0.00
• Training Generalizable Collaborative Agents Via Strategic Risk Aversion (2026)0.00
• Cooperation Dynamics In Multi-agent Systems: Exploring Game-theoretic Scenarios With Mean-field Equilibria (2023)0.00
• Intrinsic Fluctuations Of Reinforcement Learning Promote Cooperation (2022)9.23
• Cooperative Artificial Intelligence (2022)0.00