We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such that the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable. We evaluate our algorithm on several large scale challenging tasks and demonstrate that it outperforms previous state-of-the-arts.
@article{arxiv.2004.08883,
title = {Variational Policy Propagation for Multi-agent Reinforcement Learning},
author = {Chao Qu and Hui Li and Chang Liu and Junwu Xiong and James Zhang and Wei Chu and Weiqiang Wang and Yuan Qi and Le Song},
journal= {arXiv preprint arXiv:2004.08883},
year = {2022}
}
Comments
The title of previous version was "Intention Propagation for Multi-agent Reinforcement Learning"