Q-learning with experience replay in a dynamic environment

Mathijs Pieters, M. Wiering
{"title":"Q-learning with experience replay in a dynamic environment","authors":"Mathijs Pieters, M. Wiering","doi":"10.1109/SSCI.2016.7849368","DOIUrl":null,"url":null,"abstract":"Most research in reinforcement learning has focused on stationary environments. In this paper, we propose several adaptations of Q-learning for a dynamic environment, for both single and multiple agents. The environment consists of a grid of random rewards, where every reward is removed after a visit. We focus on experience replay, a technique that receives a lot of attention nowadays, and combine this method with Q-learning. We compare two variations of experience replay, where experiences are reused based on time or based on the obtained reward. For multi-agent reinforcement learning we compare two variations of policy representation. In the first variation the agents share a Q-function, while in the second variation both agents have a separate Q-function. Furthermore, in both variations we test the effect of reward sharing between the agents. This leads to four different multi-agent reinforcement learning algorithms, from which sharing a Q-function and sharing the rewards is the most cooperative method. The results show that in the single-agent environment both experience replay algorithms significantly outperform standard Q-learning and a greedy benchmark agent. In the multi-agent environment the highest maximum reward sum in a trial is achieved by using one Q-function and reward sharing. The highest mean reward sum is obtained with separate Q-functions and separate rewards.","PeriodicalId":120288,"journal":{"name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2016-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"20","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SSCI.2016.7849368","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 20

Abstract

Most research in reinforcement learning has focused on stationary environments. In this paper, we propose several adaptations of Q-learning for a dynamic environment, for both single and multiple agents. The environment consists of a grid of random rewards, where every reward is removed after a visit. We focus on experience replay, a technique that receives a lot of attention nowadays, and combine this method with Q-learning. We compare two variations of experience replay, where experiences are reused based on time or based on the obtained reward. For multi-agent reinforcement learning we compare two variations of policy representation. In the first variation the agents share a Q-function, while in the second variation both agents have a separate Q-function. Furthermore, in both variations we test the effect of reward sharing between the agents. This leads to four different multi-agent reinforcement learning algorithms, from which sharing a Q-function and sharing the rewards is the most cooperative method. The results show that in the single-agent environment both experience replay algorithms significantly outperform standard Q-learning and a greedy benchmark agent. In the multi-agent environment the highest maximum reward sum in a trial is achieved by using one Q-function and reward sharing. The highest mean reward sum is obtained with separate Q-functions and separate rewards.
动态环境下的q学习与经验回放
大多数强化学习的研究都集中在固定环境上。在本文中,我们提出了几个动态环境下q -学习的适应性,包括单智能体和多智能体。游戏环境由随机奖励网格组成,玩家访问后所有奖励都会被移除。我们专注于经验回放,这是一种现在非常受关注的技术,并将这种方法与Q-learning相结合。我们比较了体验重放的两种变体,即基于时间或基于获得的奖励而重复使用体验。对于多智能体强化学习,我们比较了策略表示的两种变体。在第一个变量中,智能体共享一个q函数,而在第二个变量中,两个智能体都有一个单独的q函数。此外,在这两种变化中,我们都测试了代理之间奖励分享的影响。这导致了四种不同的多智能体强化学习算法,其中共享q函数和共享奖励是最具协作性的方法。结果表明,在单智能体环境下,两种经验重放算法的性能都明显优于标准q -学习和贪婪基准智能体。在多智能体环境中,通过使用一个q函数和奖励共享来实现一次试验中最大的奖励总和。使用单独的q函数和单独的奖励获得最高的平均奖励总和。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信