Robust Multi-agent Reinforcement Learning By Mutual Information Regularization

Abstract

In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL methods either approximate or enumerate all possible threat scenarios against worst-case adversaries, leading to computational intensity and reduced robustness. In contrast, human learning efficiently acquires robust behaviors in daily life without preparing for every possible threat. Inspired by this, we frame robust MARL as an inference problem, with worst-case robustness implicitly optimized under all threat scenarios via off-policy evaluation. Within this framework, we demonstrate that Mutual Information Regularization as Robust Regularization (MIR3) during routine training is guaranteed to maximize a lower bound on robustness, without the need for adversaries. Further insights show that MIR3 acts as an information bottleneck, preventing agents from over-reacting to others and aligning policies with robust

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2023robust

Related papers

• Robust Multi-agent Reinforcement Learning Via Adversarial Regularization: Theoretical Foundation And Stable Algorithms (2023)2.98
• Regularize! Don't Mix: Multi-agent Reinforcement Learning Without Explicit Centralized Structures (2021)0.00
• Robust Multi-agent Reinforcement Learning With State Uncertainty (2023)0.00
• Breaking The Curse Of Multiagency In Robust Multi-agent Reinforcement Learning (2024)0.00
• Empirical Study On Robustness And Resilience In Cooperative Multi-agent Reinforcement Learning (2025)0.00
• Robustness To Multi-modal Environment Uncertainty In MARL Using Curriculum Learning (2023)0.00
• PMIC: Improving Multi-agent Reinforcement Learning With Progressive Mutual Information Collaboration (2022)0.00
• ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning Via Convex Relaxation (2021)0.00