Explainable Multi-Agent Reinforcement Learning for Temporal Queries
This work addresses the problem of explainability in MARL for users, providing a method to reconcile discrepancies in multi-agent behaviors, though it is incremental as it builds on existing MARL and logic-based explanation techniques.
The paper tackles the challenge of understanding emergent behaviors in multi-agent reinforcement learning (MARL) systems by generating policy-level contrastive explanations for temporal queries, using PCTL logic and probabilistic model checking; it successfully applied the approach to four benchmark domains and a user study showed significant improvements in user performance and satisfaction.
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.