Learning Policy Representations in Multiagent Systems
This addresses the need for scalable and generalizable agent modeling in multiagent systems, which is incremental as it builds on prior imitation learning and representation learning methods.
The paper tackles the problem of modeling agent behavior in multiagent systems by proposing a general learning framework that uses only a small amount of interaction data, achieving results in competitive and cooperative environments for tasks like prediction, clustering, and policy optimization.
Modeling agent behavior is central to understanding the emergence of complex phenomena in multiagent systems. Prior work in agent modeling has largely been task-specific and driven by hand-engineering domain-specific prior knowledge. We propose a general learning framework for modeling agent behavior in any multiagent system using only a handful of interaction data. Our framework casts agent modeling as a representation learning problem. Consequently, we construct a novel objective inspired by imitation learning and agent identification and design an algorithm for unsupervised learning of representations of agent policies. We demonstrate empirically the utility of the proposed framework in (i) a challenging high-dimensional competitive environment for continuous control and (ii) a cooperative environment for communication, on supervised predictive tasks, unsupervised clustering, and policy optimization using deep reinforcement learning.