MEASE: Multi-agent Episodic Action Sequence Explanation

Khaing Phyo Wai, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Keywords: Explainable Multi-agent Reinforcement Learning; Multi-agent Reinforcement Learning; Sequential Decision Making

Abstract: Multi-agent reinforcement learning (MARL) achieves remarkable performance in complex coordination tasks, yet interpreting the emergent behaviors of trained agents remains a fundamental challenge. Most current explainability methods focus on individual agent decisions, overlooking the critical interplay of joint strategies and temporal coordination patterns that define successful multi-agent policies. We present MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors. MEASE employs a cognitive-inspired episodic memory model to learn spatio-temporal multi-agent interaction patterns, coupled with abstraction algorithms that identify significant cooperative agent behaviors. We evaluate MEASE on diverse scenarios in the VMAS and MOSMAC environments, demonstrating its generalizable ability across various tasks and domains. These explanations, which prescribe ``when to do what'' for multi-agent systems, serve as executable coordination protocols that faithfully capture the learned behaviors. Quantitative validation shows that deploying explanations as strategies achieves 93% of the original MARL policy performance. A user study with 31 participants validates the clarity and usefulness of generated explanations. These results demonstrate that MEASE effectively extracts explanatory knowledge from complex multi-agent behaviors.

Area: Representation and Reasoning (RR)

Generative A I: I acknowledge that I have read and will follow this policy.

Submission Number: 1652