Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles
This addresses the challenge of effective role decomposition in complex multi-agent tasks, offering a flexible framework for MARL, though it appears incremental as it builds on existing role-based methods.
The paper tackles the problem of stably discovering roles for multi-agent reinforcement learning without manual assistance, proposing a structural information principles-based method that improves average test win rates by up to 6.08% and reduces deviation by up to 66.30% on StarCraft II benchmarks.
Role-based learning is a promising approach to improving the performance of Multi-Agent Reinforcement Learning (MARL). Nevertheless, without manual assistance, current role-based methods cannot guarantee stably discovering a set of roles to effectively decompose a complex task, as they assume either a predefined role structure or practical experience for selecting hyperparameters. In this article, we propose a mathematical Structural Information principles-based Role Discovery method, namely SIRD, and then present a SIRD optimizing MARL framework, namely SR-MARL, for multi-agent collaboration. The SIRD transforms role discovery into a hierarchical action space clustering. Specifically, the SIRD consists of structuralization, sparsification, and optimization modules, where an optimal encoding tree is generated to perform abstracting to discover roles. The SIRD is agnostic to specific MARL algorithms and flexibly integrated with various value function factorization approaches. Empirical evaluations on the StarCraft II micromanagement benchmark demonstrate that, compared with state-of-the-art MARL algorithms, the SR-MARL framework improves the average test win rate by 0.17%, 6.08%, and 3.24%, and reduces the deviation by 16.67%, 30.80%, and 66.30%, under easy, hard, and super hard scenarios.