A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning

Abstract

This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. It is shown that the algorithm can solve the problem for strongly connected graphs by allowing each agent to transmit only two scalar-valued variables at one time.

References in corpus (4)

• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• $QD$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability