Multi-Agent Interactions Modeling with Correlated Policies

Minghuan Liu, Ming Zhou, Weinan Zhang, Yuzheng Zhuang, Jun Wang, Wulong Liu, Yong Yu

TL;DR: Modeling complex multi-agent interactions under multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents’ policies.

Abstract:

In multi-agent systems, complex interacting behaviors arise due to the high correlations among agents. However, previous work on modeling multi-agent interactions from demonstrations is primarily constrained by assuming the independence among policies and their reward structures.
In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework with explicit modeling of correlated policies by approximating opponents’ policies, which can recover agents' policies that can regenerate similar interactions. Consequently, we develop a Decentralized Adversarial Imitation Learning algorithm with Correlated policies (CoDAIL), which allows for decentralized training and execution. Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators and outperforms state-of-the-art multi-agent imitation learning methods. Our code is available at \url{https://github.com/apexrl/CoDAIL}.

Code: https://github.com/apexrl/CoDAIL

Keywords: Multi-agent reinforcement learning, Imitation learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2001.03415/code)