Our paper “Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions” has been accepted by IEEE Transactions on Automatic Control as a full paper. This is a joint work with He Bai at Oklahoma State University, Jemin George at US ARL, Aranya Chakrabortty at North Carolina State University, and Piyush K. Sharma at US ARL.

You can reach this paper via https://arxiv.org/abs/2202.13046 or doi:10.1109/TAC.2024.3375248