{"title":"Q-value-based experience replay in reinforcement learning","authors":"Zihong Zhang, 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.
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.