Context-dependent meta-control for reinforcement learning using a Dirichlet process Gaussian mixture model

Dongjae Kim, Sang Wan Lee
{"title":"Context-dependent meta-control for reinforcement learning using a Dirichlet process Gaussian mixture model","authors":"Dongjae Kim, Sang Wan Lee","doi":"10.1109/IWW-BCI.2018.8311512","DOIUrl":null,"url":null,"abstract":"Arbitration between model-based (MB) and model-free (MF) reinforcement learning (RL) is key feature of human reinforcement learning. The computational model of arbitration control has been demonstrated to outperform conventional reinforcement learning algorithm, in terms of not only behavioral data but also neural signals. However, this arbitration process does not take full account of contextual changes in environment during learning. By incorporating a Dirichlet process Gaussian mixture model into the arbitration process, we propose a meta-controller for RL that quickly adapts to contextual changes of environment. The proposed model performs better than a conventional model-free RL, model-based RL, and arbitration model.","PeriodicalId":6537,"journal":{"name":"2018 6th International Conference on Brain-Computer Interface (BCI)","volume":"27 1","pages":"1-3"},"PeriodicalIF":0.0000,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 6th International Conference on Brain-Computer Interface (BCI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWW-BCI.2018.8311512","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Arbitration between model-based (MB) and model-free (MF) reinforcement learning (RL) is key feature of human reinforcement learning. The computational model of arbitration control has been demonstrated to outperform conventional reinforcement learning algorithm, in terms of not only behavioral data but also neural signals. However, this arbitration process does not take full account of contextual changes in environment during learning. By incorporating a Dirichlet process Gaussian mixture model into the arbitration process, we propose a meta-controller for RL that quickly adapts to contextual changes of environment. The proposed model performs better than a conventional model-free RL, model-based RL, and arbitration model.
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
使用狄利克雷过程高斯混合模型的强化学习的上下文相关元控制
基于模型(MB)和无模型(MF)的强化学习(RL)之间的仲裁是人类强化学习的关键特征。仲裁控制的计算模型不仅在行为数据方面,而且在神经信号方面都优于传统的强化学习算法。然而,这种仲裁过程并没有充分考虑到学习过程中环境的上下文变化。通过将Dirichlet过程高斯混合模型纳入仲裁过程,我们提出了一种快速适应环境上下文变化的强化学习元控制器。该模型的性能优于传统的无模型RL、基于模型的RL和仲裁模型。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Embodied cognition Design of a brain-controlled robot arm system based on upper-limb movement imagery Applying deep-learning to a top-down SSVEP BMI BCI classification using locally generated CSP features Evaluation of outlier prevalence of density distribution in brain computed tomography: Comparison of kurtosis and quartile statistics
×
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