arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.00260math.OCcs.LG
收藏

异步随机逼近的实时分析与$Q$学习

Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning

California Institute of Technology(加州理工学院)

Guannan Qu, Adam Wierman

摘要:

考虑了一个加权无穷范数压缩算子的一般异步随机逼近(SA)格式,并证明了其在单个轨迹上的有限时间收敛速度的一个界.此外,我们专门的异步$Q$学习的结果。所得到的界限匹配同步$Q$学习的最清晰的可用界限,并且改进了异步$Q$学习的先前已知界限。

英文摘要:

We consider a general asynchronous Stochastic Approximation (SA) scheme featuring a weighted infinity-norm contractive operator, and prove a bound on its finite-time convergence rate on a single trajectory. Additionally, we specialize the result to asynchronous $Q$-learning. The resulting bound matches the sharpest available bound for synchronous $Q$-learning, and improves over previous known bounds for asynchronous $Q$-learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑