arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.02847stat.MLcs.LG
收藏

马尔可夫决策过程中的最佳策略

Navigating to the Best Policy in Markov Decision Processes

ENS Lyon(里昂高等师范学院);CNRS(法国国家科学研究中心);INRIA(法国国家信息与自动化研究所);KTH Royal Institute of Technology(瑞典皇家理工学院)

Aymen Al Marjani, Aurélien Garivier, Alexandre Proutiere

摘要:

我们研究了经典的主动纯探索问题在马尔可夫决策过程中,代理顺序选择的行动,并从由此产生的系统轨迹,旨在确定尽可能快的最佳政策。我们提出了一个问题相关的下限的平均步骤数之前,可以给出一个正确的答案,概率至少$1-δ$。我们进一步提供了第一个算法,在此设置中具有特定于实例的样本复杂度。该算法解决了通信MDP的一般情况下,我们还提出了一个额外的遍历性假设下的探索率降低(因此收敛速度更快)的变体。这项工作扩展了以前的结果相对于\emph{generative setting} ~ \cite{pmlr-v139-marjani21a},其中代理可以在每一步查询任何(状态,动作)对的随机结果。相反,我们在这里展示如何处理由\emph{online setting}诱导的\emph{navigation constraints}。我们的分析依赖于遍历定理的非齐次马尔可夫链,我们认为广泛的兴趣在马尔可夫决策过程的分析。

英文摘要:

We investigate the classical active pure exploration problem in Markov Decision Processes, where the agent sequentially selects actions and, from the resulting system trajectory, aims at identifying the best policy as fast as possible. We propose a problem-dependent lower bound on the average number of steps required before a correct answer can be given with probability at least $1-δ$. We further provide the first algorithm with an instance-specific sample complexity in this setting. This algorithm addresses the general case of communicating MDPs; we also propose a variant with a reduced exploration rate (and hence faster convergence) under an additional ergodicity assumption. This work extends previous results relative to the \emph{generative setting}~\cite{pmlr-v139-marjani21a}, where the agent could at each step query the random outcome of any (state, action) pair. In contrast, we show here how to deal with the \emph{navigation constraints}, induced by the \emph{online setting}. Our analysis relies on an ergodic theorem for non-homogeneous Markov chains which we consider of wide interest in the analysis of Markov Decision Processes.

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。

↑