MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search
This addresses efficiency problems for researchers and practitioners in multi-agent systems, though it is incremental as it builds on existing deep MARL algorithms.
The paper tackles the slow training and convergence issues in cooperative multi-agent reinforcement learning by proposing MARL-LNS, a framework that trains on alternating subsets of agents, reducing training time by at least 10% while maintaining the same final skill level.
Cooperative multi-agent reinforcement learning (MARL) has been an increasingly important research topic in the last half-decade because of its great potential for real-world applications. Because of the curse of dimensionality, the popular "centralized training decentralized execution" framework requires a long time in training, yet still cannot converge efficiently. In this paper, we propose a general training framework, MARL-LNS, to algorithmically address these issues by training on alternating subsets of agents using existing deep MARL algorithms as low-level trainers, while not involving any additional parameters to be trained. Based on this framework, we provide three algorithm variants based on the framework: random large neighborhood search (RLNS), batch large neighborhood search (BLNS), and adaptive large neighborhood search (ALNS), which alternate the subsets of agents differently. We test our algorithms on both the StarCraft Multi-Agent Challenge and Google Research Football, showing that our algorithms can automatically reduce at least 10% of training time while reaching the same final skill level as the original algorithm.