arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2212.06355stat.MLcs.LGmath.STstat.MEstat.TH
收藏

强化学习中的非策略评估研究综述

A Review of Off-Policy Evaluation in Reinforcement Learning

Cornell University(康奈尔大学);Cornell Tech(康奈尔理工学院);London School of Economics and Political Science(伦敦政治经济学院)

Masatoshi Uehara, Chengchun Shi, Nathan Kallus

摘要:

强化学习(RL)是机器学习中最具活力的研究前沿之一,最近已被应用于解决许多具有挑战性的问题。在本文中,我们主要关注的政策外评估(OPE),在RL的最基本的主题之一。近年来,在统计学和计算机科学文献中开发了许多OPE方法。我们提供了一个讨论的OPE,一些现有的国家的最先进的OPE方法,其统计特性和其他一些相关的研究方向,目前正在积极探索的效率界。

英文摘要:

Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of the most fundamental topics in RL. In recent years, a number of OPE methods have been developed in the statistics and computer science literature. We provide a discussion on the efficiency bound of OPE, some of the existing state-of-the-art OPE methods, their statistical properties and some other related research directions that are currently actively explored.

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。

↑