MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning

TL;DR

This paper introduces MAVIPER, a novel method for extracting interpretable decision tree policies from neural networks trained with multi-agent reinforcement learning, improving interpretability and coordination.

Contribution

It extends single-agent interpretable RL methods to multi-agent settings and proposes a centralized training algorithm for better coordination.

Findings

MAVIPER outperforms baselines in multi-agent environments.

IVIPER learns high-quality decision-tree policies for individual agents.

MAVIPER achieves better coordination among agents.

Abstract

Many recent breakthroughs in multi-agent reinforcement learning (MARL) require the use of deep neural networks, which are challenging for human experts to interpret and understand. On the other hand, existing work on interpretable reinforcement learning (RL) has shown promise in extracting more interpretable decision tree-based policies from neural networks, but only in the single-agent setting. To fill this gap, we propose the first set of algorithms that extract interpretable decision-tree policies from neural networks trained with MARL. The first algorithm, IVIPER, extends VIPER, a recent method for single-agent interpretable RL, to the multi-agent setting. We demonstrate that IVIPER learns high-quality decision-tree policies for each agent. To better capture coordination between agents, we propose a novel centralized decision-tree training algorithm, MAVIPER. MAVIPER jointly grows the trees of each agent by predicting the behavior of the other agents using their anticipated trees, and uses resampling to focus on states that are critical for its interactions with other agents. We show that both algorithms generally outperform the baselines and that MAVIPER-trained agents achieve better-coordinated performance than IVIPER-trained agents on three different multi-agent particle-world environments.