arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.09083math.STcs.LGmath.OCstat.TH
收藏

马尔可夫决策过程中后验分布的收敛速度

Convergence Rates of Posterior Distributions in Markov Decision Process

NC State University(北卡罗来纳州立大学)

Zhen Li, Eric Laber

摘要:

在本文中,我们显示的收敛速度的后验分布的模型动力学在MDP的情节和连续的任务。理论结果适用于一般的状态和动作空间,动力学的参数空间可以是无穷维的。此外,我们还证明了在固定策略或最优策略下,平均累积报酬的后验分布和后悔界的收敛速度。提出了一种改进的Thompson采样算法,它既能提供动力学的后验收敛速度,又能提供后悔型界。然后将已有的结果推广到马尔可夫对策。最后,我们展示了三种模拟场景的数值结果,并进行了讨论。

英文摘要:

In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks. The theoretical results hold for general state and action space and the parameter space of the dynamics can be infinite dimensional. Moreover, we show the convergence rates of posterior distributions of the mean accumulative reward under a fixed or the optimal policy and of the regret bound. A variant of Thompson sampling algorithm is proposed which provides both posterior convergence rates for the dynamics and the regret-type bound. Then the previous results are extended to Markov games. Finally, we show numerical results with three simulation scenarios and conclude with discussions.

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。

↑