An Asynchronous Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning-猫眼课题宝

DOI：

发表时间：

2019

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Yixuan Lin;Yu-Juan Luo;K. Zhang;Zhuoran Yang;Zhaoran Wang;T. Başar;Romeil Sandhu;Ji Liu

本文研究了一个分布式强化学习问题，其中多个代理网络旨在通过仅与本地邻居进行通信来合作最大化全局平均回报。针对有向图描述的可能的单向通信关系，提出了一种异步多代理演员-批评家算法。每个代理在由自己的时钟确定的“事件时间”独立更新其变量。不假设代理的时钟是同步的或者事件时间是均匀间隔的。结果表明，该算法可以解决存在通信和计算延迟的任何强连通图的问题

This paper studies a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. An asynchronous multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. Each agent independently updates its variables at “event times” determined by its own clock. It is not assumed that the agents’ clocks are synchronized or that the event times are evenly spaced. It is shown that the algorithm can solve the problem for any strongly connected graph in the presence of communication and computation delays

An Asynchronous Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning

文献摘要

相似文献