文件名称:policygradientlibrary
介绍说明--下载内容均来自于网络,请自行研究使用
策略梯度,自然策略梯度,行动者-评论家
-policy gradient
-policy gradient
(系统自动生成,下载前可以参看下载内容)
下载文件列表
policygradientlibrary
.....................\.DS_Store
__MACOSX
........\policygradientlibrary
........\.....................\._.DS_Store
policygradientlibrary\Examples
.....................\........\#LQR_1d_DF.m#
.....................\........\.#LQR_1d_DF.m
.....................\........\approximateAdvantageTDLearning.m~
.....................\........\Bartlett.m
.....................\........\Bartlett.m~
.....................\........\cartandpole.m
.....................\........\cartpl.m
.....................\........\cartpl.m~
.....................\........\example.m~
.....................\........\LQR_1d_AF.m
.....................\........\LQR_1d_DF.m
.....................\........\LQR_1d_DF.m~
.....................\........\LQR_1d_DF_Gradients.m
.....................\........\LQR_2d_DF.m
.....................\........\MountainCar.m
.....................\........\OneState.m
.....................\........\testHOM.m
.....................\........\testHOM.m~
.....................\........\testLQRN.m
.....................\........\testLQRN.m~
.....................\........\testLQRNN.m
.....................\........\TwoState_AF.m
.....................\........\TwoState_AF.m~
.....................\........\TwoState_DF.m
.....................\........\TwoState_DF_Gradient.m
.....................\install.m
.....................\Library
.....................\.......\ActorCritic.m~
.....................\.......\advantageTDLearning.m
.....................\.......\advantageTDLearning.m~
.....................\.......\AFnc.m
.....................\.......\AFnc.m~
.....................\.......\AllActionGradient.m
.....................\.......\allActionMatrix.m
.....................\.......\approximateAdvantageTDLearning.m
__MACOSX\policygradientlibrary\Library
........\.....................\.......\._approximateAdvantageTDLearning.m
policygradientlibrary\Library\approximateAdvantageTDLearning.m~
.....................\.......\approximateTDLearning.m
.....................\.......\directApproximation.m
.....................\.......\discountedDistribution.m
.....................\.......\DlogPiDTheta.m
.....................\.......\DlogPiDTheta.m~
.....................\.......\drawAction.m
.....................\.......\drawFromTable.m
.....................\.......\drawNextState.m
.....................\.......\drawStartState.m
.....................\.......\episodicNaturalActorCritic.m
__MACOSX\policygradientlibrary\Library\._episodicNaturalActorCritic.m
policygradientlibrary\Library\episodicREINFORCE.m
.....................\.......\estimateAllActionMatrix.m
.....................\.......\expectedReturn.m
.....................\.......\GPOMDP.m
.....................\.......\learnThroughValueFunction.m
__MACOSX\policygradientlibrary\Library\._learnThroughValueFunction.m
policygradientlibrary\Library\learnValueFunction.m
.....................\.......\learnValueFunction.m~
.....................\.......\LSTDQ.m
.....................\.......\naturalActorCritic.m
__MACOSX\policygradientlibrary\Library\._naturalActorCritic.m
policygradientlibrary\Library\naturalPolicyGradient.m
.....................\.......\nonepisodicREINFORCE.m
.....................\.......\nonepisodicREINFORCE.m~
.....................\.......\obtainData.m
.....................\.......\oneStepTransitionKernel.m
.....................\.......\optimalSolution.m
.....................\.......\optimalSolution.m~
.....................\.......\pi_theta.m
.....................\.......\pointFisherMatrix.m
.....................\.......\policyEvaluation.m
.....................\.......\policyGradient.m
.....................\.......\PTLSTD.m
.....................\.......\QFnc.m
.....................\.......\resolvantKernel.m
.....................\.......\rewardFnc.m
.....................\.......\ricatti.m
.....................\.......\ricatti.m~
.....................\.......\SampleBasedGradient.m
.....................\.......\samplePathLearning.m~
.....................\.......\SARSA.m
.....................\.......\stationaryDistribution.m
.....................\.......\stationaryDistribution.