前瞻性和近似策略评估在线性值函数近似强化学习中的作用

IF 2.2 3区管理学 Q3 MANAGEMENT

Operations Research Pub Date : 2024-05-30 DOI:10.1287/opre.2022.0357

Anna Winnicki, Joseph Lubars, Michael Livesay, R. Srikant

引用次数: 0

摘要

运筹学》，印刷版前。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The Role of Lookahead and Approximate Policy Evaluation in Reinforcement Learning with Linear Value Function Approximation

Operations Research, Ahead of Print.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Operations Research 管理科学-运筹学与管理科学

CiteScore

4.80

自引率

14.80%

发文量

237

审稿时长

15 months

期刊介绍： Operations Research publishes quality operations research and management science works of interest to the OR practitioner and researcher in three substantive categories: methods, data-based operational science, and the practice of OR. The journal seeks papers reporting underlying data-based principles of operational science, observations and modeling of operating systems, contributions to the methods and models of OR, case histories of applications, review articles, and discussions of the administrative environment, history, policy, practice, future, and arenas of application of operations research.