Breaking The Curse Of Multiagency In Robust Multi-agent Reinforcement Learning

Abstract

Standard multi-agent reinforcement learning (MARL) algorithms are vulnerable to sim-to-real gaps. To address this, distributionally robust Markov games (RMGs) have been proposed to enhance robustness in MARL by optimizing the worst-case performance when game dynamics shift within a prescribed uncertainty set. RMGs remains under-explored, from reasonable problem formulation to the development of sample-efficient algorithms. Two notorious and open challenges are the formulation of the uncertainty set and whether the corresponding RMGs can overcome the curse of multiagency, where the sample complexity scales exponentially with the number of agents. In this work, we propose a natural class of RMGs inspired by behavioral economics, where each agent's uncertainty set is shaped by both the environment and the integrated behavior of other agents. We first establish the well-posedness of this class of RMGs by proving the existence of game-theoretic solutions such as robust Nash equilibria and c

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshi2024breaking

Related papers

• Robust Multi-agent Reinforcement Learning With State Uncertainty (2023)0.00
• Sample-efficient Robust Multi-agent Reinforcement Learning In The Face Of Environmental Uncertainty (2024)0.00
• Minimax-optimal Multi-agent Robust Reinforcement Learning (2024)0.00
• Incentivize Without Bonus: Provably Efficient Model-based Online Multi-agent RL For Markov Games (2025)0.00
• Sample-efficient Distributionally Robust Multi-agent Reinforcement Learning Via Online Interaction (2025)0.00
• Risk-sensitive Multi-agent Reinforcement Learning In Network Aggregative Markov Games (2024)0.00
• Breaking The Curse Of Multiagency: Provably Efficient Decentralized Multi-agent RL With Function Approximation (2023)0.00
• Byzantine Robust Cooperative Multi-agent Reinforcement Learning As A Bayesian Game (2023)0.00