English

Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph

Multiagent Systems 2022-01-14 v1 Artificial Intelligence Machine Learning Systems and Control Systems and Control Optimization and Control

Abstract

Existing distributed cooperative multi-agent reinforcement learning (MARL) frameworks usually assume undirected coordination graphs and communication graphs while estimating a global reward via consensus algorithms for policy evaluation. Such a framework may induce expensive communication costs and exhibit poor scalability due to requirement of global consensus. In this work, we study MARLs with directed coordination graphs, and propose a distributed RL algorithm where the local policy evaluations are based on local value functions. The local value function of each agent is obtained by local communication with its neighbors through a directed learning-induced communication graph, without using any consensus algorithm. A zeroth-order optimization (ZOO) approach based on parameter perturbation is employed to achieve gradient estimation. By comparing with existing ZOO-based RL algorithms, we show that our proposed distributed RL algorithm guarantees high scalability. A distributed resource allocation example is shown to illustrate the effectiveness of our algorithm.

Keywords

Cite

@article{arxiv.2201.04962,
  title  = {Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph},
  author = {Gangshan Jing and He Bai and Jemin George and Aranya Chakrabortty and Piyush. K. Sharma},
  journal= {arXiv preprint arXiv:2201.04962},
  year   = {2022}
}
R2 v1 2026-06-24T08:48:55.986Z