Explainable Multi-Agent Reinforcement Learning for Temporal Queries

TL;DR

This paper introduces a method for generating explainable, policy-level contrastive explanations for multi-agent reinforcement learning systems to improve user understanding of complex, temporal behaviors.

Contribution

It presents a novel approach that encodes temporal user queries as PCTL formulas and uses probabilistic model checking to generate complete explanations for MARL behaviors.

Findings

Successfully applied to four benchmark MARL domains with up to 9 agents.

Generated explanations significantly improved user performance.

User satisfaction increased with the proposed explanation method.

Abstract

As multi-agent reinforcement learning (MARL) systems are increasingly deployed throughout society, it is imperative yet challenging for users to understand the emergent behaviors of MARL agents in complex environments. This work presents an approach for generating policy-level contrastive explanations for MARL to answer a temporal user query, which specifies a sequence of tasks completed by agents with possible cooperation. The proposed approach encodes the temporal query as a PCTL logic formula and checks if the query is feasible under a given MARL policy via probabilistic model checking. Such explanations can help reconcile discrepancies between the actual and anticipated multi-agent behaviors. The proposed approach also generates correct and complete explanations to pinpoint reasons that make a user query infeasible. We have successfully applied the proposed approach to four benchmark MARL domains (up to 9 agents in one domain). Moreover, the results of a user study show that the generated explanations significantly improve user performance and satisfaction.