Agent Modeling as Auxiliary Task for Deep Reinforcement Learning
This work addresses the challenge of learning effective policies in multiagent environments for AI systems, though it appears incremental as it builds on existing actor-critic methods.
The paper tackles the problem of improving deep reinforcement learning in multiagent settings by extending actor-critic methods with agent modeling as an auxiliary task, resulting in stabilized learning and outperforming standard A3C in terms of expected rewards in cooperative and competitive domains.
In this paper we explore how actor-critic methods in deep reinforcement learning, in particular Asynchronous Advantage Actor-Critic (A3C), can be extended with agent modeling. Inspired by recent works on representation learning and multiagent deep reinforcement learning, we propose two architectures to perform agent modeling: the first one based on parameter sharing, and the second one based on agent policy features. Both architectures aim to learn other agents' policies as auxiliary tasks, besides the standard actor (policy) and critic (values). We performed experiments in both cooperative and competitive domains. The former is a problem of coordinated multiagent object transportation and the latter is a two-player mini version of the Pommerman game. Our results show that the proposed architectures stabilize learning and outperform the standard A3C architecture when learning a best response in terms of expected rewards.