Information-Bottleneck-Based Behavior Representation Learning for Multi-agent Reinforcement learning
This work addresses the challenge of efficient and scalable learning in multi-agent systems, offering an incremental improvement over prior representation learning approaches.
The paper tackles the problem of extracting compact and informative behavior representations of other agents in multi-agent reinforcement learning by proposing IBORM, which uses the information bottleneck principle to explicitly compress observations while retaining relevant information, resulting in the fastest convergence rate and best policy performance compared to existing methods.
In multi-agent deep reinforcement learning, extracting sufficient and compact information of other agents is critical to attain efficient convergence and scalability of an algorithm. In canonical frameworks, distilling of such information is often done in an implicit and uninterpretable manner, or explicitly with cost functions not able to reflect the relationship between information compression and utility in representation. In this paper, we present Information-Bottleneck-based Other agents' behavior Representation learning for Multi-agent reinforcement learning (IBORM) to explicitly seek low-dimensional mapping encoder through which a compact and informative representation relevant to other agents' behaviors is established. IBORM leverages the information bottleneck principle to compress observation information, while retaining sufficient information relevant to other agents' behaviors used for cooperation decision. Empirical results have demonstrated that IBORM delivers the fastest convergence rate and the best performance of the learned policies, as compared with implicit behavior representation learning and explicit behavior representation learning without explicitly considering information compression and utility.