Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning
This addresses the need for better interpretability in multi-agent systems, which is crucial for applications like policy understanding and security, though it is an incremental improvement over existing explanation methods.
The paper tackled the problem of explaining individual agent importance in multi-agent systems by proposing EMAI, a novel approach using counterfactual reasoning, which achieved higher fidelity in explanations than baselines across seven tasks.
Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has proveided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent's importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent's importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstratee that EMAI achieves higher fidelity in explanations than baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies.