Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph. (arXiv:2201.04962v1 [cs.MA])

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 …

arxiv distributed graph learning reinforcement learning