arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.10916math.OCcs.LG
收藏

基于Monte Carlo探索启动的强化学习收敛性研究

On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts

University of Waterloo(滑铁卢大学)

Jun Liu

摘要:

一种基本的基于模拟的强化学习算法是蒙特卡洛探索状态(Monte Carlo Exploring States,MCES)方法,也称为乐观策略迭代,其中值函数由模拟返回近似,并且在每次迭代时选择贪婪策略。该算法在一般情况下的收敛性一直是一个悬而未决的问题。在本文中,我们研究了该算法的收敛性的情况下,与未贴现成本,也被称为随机最短路问题。这些结果补充了已有的部分结果,从而有助于进一步解决这一问题。作为一个附带的结果,我们还提供了一个版本的上鞅收敛定理通常用于随机逼近的证明。

英文摘要:

A basic simulation-based reinforcement learning algorithm is the Monte Carlo Exploring States (MCES) method, also known as optimistic policy iteration, in which the value function is approximated by simulated returns and a greedy policy is selected at each iteration. The convergence of this algorithm in the general setting has been an open question. In this paper, we investigate the convergence of this algorithm for the case with undiscounted costs, also known as the stochastic shortest path problem. The results complement existing partial results on this topic and thereby helps further settle the open problem. As a side result, we also provide a proof of a version of the supermartingale convergence theorem commonly used in stochastic approximation.

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。

↑