Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

5-2026

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 strategiesand 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 cognition-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 generalizability across various tasksand domains. These explanations, which prescribe "when to do what" for multi-agent systems, serve as executable coordination protocols that faithfully capture the learned behaviors. Quantitativevalidation 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 the explanations. These results demonstrate that MEASE effectively extracts explanatory knowledge from complex multi-agent behaviors.

Keywords

Explainable Multi-agent Reinforcement Learning, Multi-agent Reinforcement Learning, Sequential Decision-making

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems, Paphos, Cyprus, 2026 May 25-29

First Page

1

Last Page

10

Publisher

International Foundation for Autonomous Agents and Multiagent Systems

City or Country

Richland, SC

Download

Share

COinS