Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

5-2024

Abstract

This paper introduces a method to explain MADRL agents’ behaviors by abstracting their actions into high-level strategies. Particularly, a spatio-temporal neural network model is applied to encode the agents’ sequences of actions as memory episodes wherein an aggregating memory retrieval can generalize them into a concise abstract representation of collective strategies. To assess the effectiveness of our method, we applied it to explain the actions of QMIX MADRL agents playing a StarCraft Multi-agent Challenge (SMAC) video game. A user study on the perceived explainability of the extracted strategies indicates that our method can provide comprehensible explanations at various levels of granularity.

Keywords

Multi-agent Deep Reinforcement Learning; Explainable Artificial Intelligence; Sequential Decision Making

Discipline

Databases and Information Systems

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024) : Auckland, New Zealand, May 6-10

First Page

2537

Last Page

2539

ISBN

9798400704864

Publisher

International Foundation for Autonomous Agents and Multiagent Systems

City or Country

Auckland, New Zealand

Comments

PDF provided by faculty

Share

COinS