奖励——机器引导、自定进度的强化学习

Cevahir Köprülü, U. Topcu
{"title":"奖励——机器引导、自定进度的强化学习","authors":"Cevahir Köprülü, U. Topcu","doi":"10.5555/3545946.3598964","DOIUrl":null,"url":null,"abstract":"Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in long-horizon planning tasks that involve temporally extended behaviors. We hypothesize that taking advantage of prior knowledge about the underlying task structure can improve the effectiveness of self-paced RL. We develop a self-paced RL algorithm guided by reward machines, i.e., a type of finite-state machine that encodes the underlying task structure. The algorithm integrates reward machines in 1) the update of the policy and value functions obtained by any RL algorithm of choice, and 2) the update of the automated curriculum that generates context distributions. Our empirical results evidence that the proposed algorithm achieves optimal behavior reliably even in cases in which existing baselines cannot make any meaningful progress. It also decreases the curriculum length and reduces the variance in the curriculum generation process by up to one-fourth and four orders of magnitude, respectively.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Reward-Machine-Guided, Self-Paced Reinforcement Learning\",\"authors\":\"Cevahir Köprülü, U. Topcu\",\"doi\":\"10.5555/3545946.3598964\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in long-horizon planning tasks that involve temporally extended behaviors. We hypothesize that taking advantage of prior knowledge about the underlying task structure can improve the effectiveness of self-paced RL. We develop a self-paced RL algorithm guided by reward machines, i.e., a type of finite-state machine that encodes the underlying task structure. The algorithm integrates reward machines in 1) the update of the policy and value functions obtained by any RL algorithm of choice, and 2) the update of the automated curriculum that generates context distributions. Our empirical results evidence that the proposed algorithm achieves optimal behavior reliably even in cases in which existing baselines cannot make any meaningful progress. It also decreases the curriculum length and reduces the variance in the curriculum generation process by up to one-fourth and four orders of magnitude, respectively.\",\"PeriodicalId\":326727,\"journal\":{\"name\":\"Adaptive Agents and Multi-Agent Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Adaptive Agents and Multi-Agent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5555/3545946.3598964\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adaptive Agents and Multi-Agent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5555/3545946.3598964","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

自进度强化学习(RL)旨在通过自动创建上下文概率分布序列(即课程)来提高学习的数据效率。然而,现有的自定节奏强化学习技术在涉及时间扩展行为的长期规划任务中失败。我们假设利用对潜在任务结构的先验知识可以提高自定节奏强化学习的有效性。我们开发了一种由奖励机器引导的自定节奏RL算法,即一种编码底层任务结构的有限状态机。该算法将奖励机器集成在以下方面:1)任何RL算法所获得的策略和价值函数的更新,以及2)生成上下文分布的自动化课程的更新。我们的经验结果表明,即使在现有基线无法取得任何有意义的进展的情况下,所提出的算法也能可靠地实现最优行为。它还减少了课程长度,并减少了课程生成过程中的差异,分别减少了四分之一和四个数量级。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Reward-Machine-Guided, Self-Paced Reinforcement Learning
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in long-horizon planning tasks that involve temporally extended behaviors. We hypothesize that taking advantage of prior knowledge about the underlying task structure can improve the effectiveness of self-paced RL. We develop a self-paced RL algorithm guided by reward machines, i.e., a type of finite-state machine that encodes the underlying task structure. The algorithm integrates reward machines in 1) the update of the policy and value functions obtained by any RL algorithm of choice, and 2) the update of the automated curriculum that generates context distributions. Our empirical results evidence that the proposed algorithm achieves optimal behavior reliably even in cases in which existing baselines cannot make any meaningful progress. It also decreases the curriculum length and reduces the variance in the curriculum generation process by up to one-fourth and four orders of magnitude, respectively.
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
自引率
0.00%
发文量
0
期刊最新文献
Discovering Consistent Subelections Strategic Cost Selection in Participatory Budgeting Minimizing State Exploration While Searching Graphs with Unknown Obstacles vMFER: von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement of Actor-Critic Algorithms Reinforcement Nash Equilibrium Solver
×
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