Q-value-based experience replay in reinforcement learning

IF 7.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Knowledge-Based Systems Pub Date : 2025-03-08 DOI:10.1016/j.knosys.2025.113296
Zihong Zhang, Ruijia Li
{"title":"Q-value-based experience replay in reinforcement learning","authors":"Zihong Zhang,&nbsp;Ruijia Li","doi":"10.1016/j.knosys.2025.113296","DOIUrl":null,"url":null,"abstract":"<div><div>Experience replay has long been used in reinforcement learning to store and reuse past experiences. However, most existing experience replay methods sample experiences with non-uniform probabilities that are proportional to their values, such as temporal-difference errors, which often lead to biased learning. To address this issue, we propose a new experience replay method that hierarchically samples experiences based on Q-values. Specifically, the proposed method divides a set of uniformly sampled experiences into three groups of the same size according to the Q-values and then uniformly samples the same number of experiences from the three groups as a mini-batch. In this manner, the sampled experiences can effectively maintain diversity. Moreover, to estimate the Q-value accurately, we develop a new critic network based on the self-attention mechanism. We integrate the new experience replay method and critic network into the twin delayed deep deterministic policy gradient algorithm to form a new reinforcement learning algorithm. An extensive set of experiments using several standard benchmarks demonstrates the effectiveness of the proposed algorithm.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"315 ","pages":"Article 113296"},"PeriodicalIF":7.2000,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705125003430","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Experience replay has long been used in reinforcement learning to store and reuse past experiences. However, most existing experience replay methods sample experiences with non-uniform probabilities that are proportional to their values, such as temporal-difference errors, which often lead to biased learning. To address this issue, we propose a new experience replay method that hierarchically samples experiences based on Q-values. Specifically, the proposed method divides a set of uniformly sampled experiences into three groups of the same size according to the Q-values and then uniformly samples the same number of experiences from the three groups as a mini-batch. In this manner, the sampled experiences can effectively maintain diversity. Moreover, to estimate the Q-value accurately, we develop a new critic network based on the self-attention mechanism. We integrate the new experience replay method and critic network into the twin delayed deep deterministic policy gradient algorithm to form a new reinforcement learning algorithm. An extensive set of experiments using several standard benchmarks demonstrates the effectiveness of the proposed algorithm.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Knowledge-Based Systems
Knowledge-Based Systems 工程技术-计算机:人工智能
CiteScore
14.80
自引率
12.50%
发文量
1245
审稿时长
7.8 months
期刊介绍: Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.
期刊最新文献
Editorial Board Graph knowledge tracing in cognitive situation: Validation of classic assertions in cognitive psychology Occluded human pose estimation based on part-aware discrete diffusion priors The evolution of cooperation in continuous dilemmas via multi-agent reinforcement learning Q-value-based experience replay in reinforcement learning
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1