返回
reinforcement learning - an introduction, second edition_bookdraft2018

reinforcement learning - an introduction, second edition_bookdraft2018

ID：31656910

大小：18.44 MB

页数：548页

时间：2019-01-16

reinforcement learning - an introduction, second edition_bookdraft2018_第1页
reinforcement learning - an introduction, second edition_bookdraft2018_第2页
reinforcement learning - an introduction, second edition_bookdraft2018_第3页
reinforcement learning - an introduction, second edition_bookdraft2018_第4页
reinforcement learning - an introduction, second edition_bookdraft2018_第5页
资源描述：

《reinforcement learning - an introduction, second edition_bookdraft2018》由会员上传分享，免费在线阅读，更多相关内容在学术论文-天天文库。

1、ReinforcementLearning:AnIntroductionSecondedition****Completedraft****March25,2018RichardS.SuttonandAndrewG.Bartoc2014,2015,2016,2017,2018Thetextisnowcompleteandformatted.Some guresarestillbeingre-made.Pleasesendanyerrorstorich@richsutton.com.Wearealsointerested

2、incorrectinganyim-portantomissionsintheBibliographicalandHistoricalRemarks"attheendofeachchapter.ABradfordBookTheMITPressCambridge,MassachusettsLondon,EnglandInmemoryofA.HarryKlopfContentsPrefacetotheSecondEditionixPrefacetotheFirstEditionxvSummaryofNotationxvi

3、i1Introduction11.1ReinforcementLearning............................11.2Examples....................................41.3ElementsofReinforcementLearning.....................61.4LimitationsandScope.............................71.5AnExtendedExample:Tic-Tac-Toe......

4、...............81.6Summary....................................131.7EarlyHistoryofReinforcementLearning...................13ITabularSolutionMethods232Multi-armedBandits252.1Ak-armedBanditProblem..........................252.2Action-valueMethods...................

5、..........272.3The10-armedTestbed.............................282.4IncrementalImplementation..........................302.5TrackingaNonstationaryProblem......................322.6OptimisticInitialValues............................342.7Upper-Con dence-BoundAction

6、Selection..................352.8GradientBanditAlgorithms..........................372.9AssociativeSearch(ContextualBandits)...................412.10Summary....................................42iiiivContents3FiniteMarkovDecisionProcesses473.1TheAgent{EnvironmentI

7、nterface......................473.2GoalsandRewards...............................533.3ReturnsandEpisodes.............................543.4Uni edNotationforEpisodicandContinuingTasks............573.5PoliciesandValueFunctions.........................583.6OptimalPo

8、liciesandOptimalValueFunctions...............623.7OptimalityandApproximation........................673.8Summary....................................684DynamicProgramm

当前文档最多预览五页，下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页，下载文档查看全文
温馨提示：
1. 部分包含数学公式或PPT动画的文件，查看预览时可能会显示错乱或异常，文件下载后无此问题，请放心下载。
2. 本文档由用户上传，版权归属用户，天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容，确认文档内容符合您的需求后进行下载，若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误，付费完成后未能成功下载的用户请联系客服处理。