F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning
This addresses the problem of high communication and computational costs in decentralized MARL for researchers and practitioners, though it appears incremental as it builds on existing actor-critic methods.
The paper tackles the impracticality of centralized multi-agent reinforcement learning (MARL) in complex applications by proposing a flexible fully decentralized actor-critic framework that handles large-scale cooperative settings, achieving competitive performance in experiments on Multi-agent Particle Environment and StarCraft II.
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications, due to non-interactivity between agents, curse of dimensionality and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. In this paper, we propose a flexible fully decentralized actor-critic MARL framework, which can combine most of actor-critic methods, and handle large-scale general cooperative multi-agent setting. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, our framework can achieve scalability and stability for large-scale environment and reduce information transmission, by the parameter sharing mechanism and a novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that our decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.