Multi-Agent Interactions Modeling with Correlated Policies
This work addresses the challenge of accurately modeling correlated behaviors in multi-agent systems for applications like robotics or game AI, representing an incremental improvement over existing methods.
The paper tackles the problem of modeling complex interactions in multi-agent systems by addressing the limitation of assuming independent policies, developing a decentralized adversarial imitation learning algorithm with correlated policies (CoDAIL) that regenerates interactions close to demonstrators and outperforms state-of-the-art methods.
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}.