Reinforcement Learning or Active Inference 英文参考文献.docVIP

下载本文档

13
0
约5.91万字
约 13页
2017-05-13 发布于上海
举报
版权申诉

Reinforcement Learning or Active Inference 英文参考文献.doc

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Reinforcement Learning or Active Inference 英文参考文献

ReinforcementLearningorActiveInference? KarlJ.Friston*,JeanDaunizeau,StefanJ.Kiebel TheWellcomeTrustCentreforNeuroimaging,UniversityCollegeLondon,London,UnitedKingdom Abstract Thispaperquestionstheneedforreinforcementlearningorcontroltheorywhenoptimisingbehaviour.Weshowthatitis fairlysimpletoteachanagentcomplicatedandadaptivebehavioursusingafree-energyformulationofperception.Inthis formulation,agentsadjusttheirinternalstatesandsamplingoftheenvironmenttominimizetheirfree-energy.Suchagents learn causal structure in the environment and sample it in an adaptive and self-supervised fashion. This results in behaviouralpoliciesthatreproducethoseoptimisedbyreinforcementlearninganddynamicprogramming.Critically,wedo not need to invoke the notion of reward, value or utility. We illustrate these points by solving a benchmark problem in dynamic programming; namely the mountain-car problem, using active perception or inference under the free-energy principle.Theensuingproof-of-conceptmaybeimportantbecausethefree-energyformulationfurnishesaunifiedaccount ofbothactionandperceptionandmayspeaktoareappraisaloftheroleofdopamineinthebrain. Citation:FristonKJ,DaunizeauJ,KiebelSJ(2009)ReinforcementLearningorActiveInference?.PLoSONE4(7):e6421.doi:10.1371/journal.pone.0006421 Editor:OlafSporns,IndianaUniversity,UnitedStatesofAmerica ReceivedFebruary12,2009;AcceptedMarch19,2009;PublishedJuly29,2009 Copyright: ? 2009 Friston et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricteduse,distribution,andreproductioninanymedium,providedtheoriginalauthorandsourcearecredited. Funding:TheWellcomeTrust:Grant#:WT056750;Modellingfunctionalbrainarchitecture.Thefundershadnoroleinstudydesign,datacollectionandanalysis, decisiontopublish,orpreparationofthemanuscript. CompetingInterests:Theauthorshavedeclaredthatnocompetinginterestsexist. *E-mail:k.friston@fil.ion.ucl.ac.uk Introduction states it could be in. Once outside these