Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph
Jing, Gangshan, Bai, He, George, Jemin, Chakrabortty, Aranya, Sharma, Piyush. K.
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-9-2022
- Country:
- North America > United States > Oklahoma > Payne County > Stillwater (0.14)
- Genre:
- Research Report (0.40)
- Technology: