Federated Control in Markov Decision Processes

arXiv:2405.04026v1 Announce Type: cross
Abstract: We study problems of federated control in Markov Decision Processes. To solve an MDP with large state space, multiple learning agents are introduced to collaboratively learn its optimal policy without communication of locally collected experience. In our settings, these agents have limited capabilities, which means they are restricted within different regions of the overall state space during the training process. In face of the difference among restricted regions, we firstly introduce concepts of leakage probabilities …

abstract agents arxiv capabilities communication control cs.lg decision experience learn markov multiple policy processes solve space state stat.ml study type