Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent

arXiv:2107.12416v4 Announce Type: replace-cross
Abstract: Recently introduced distributed zeroth-order optimization (ZOO) algorithms have shown their utility in distributed reinforcement learning (RL). Unfortunately, in the gradient estimation process, almost all of them require random samples with the same dimension as the global variable and/or require evaluation of the global cost function, which may induce high estimation variance for large-scale networks. In this paper, we propose a novel distributed zeroth-order algorithm by leveraging the network structure inherent in the optimization objective, which …

abstract algorithms arxiv asynchronous block control cs.ai cs.lg cs.sy distributed eess.sy evaluation global gradient math.oc optimization process random reinforcement reinforcement learning samples them type utility via