policygradientlibrary
.....................\policygradientlibrary
.....................\.....................\.DS_Store
.....................\.....................\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
.....................\.....................\hs_err_pid3528.log
.....................\.....................\install.m
.....................\.....................\Library
.....................\.....................\.......\ActorCritic.m~
.....................\.....................\.......\advantageTDLearning.m
.....................\.....................\.......\advantageTDLearning.m~
.....................\.....................\.......\AFnc.m
.....................\.....................\.......\AFnc.m~
.....................\.....................\.......\AllActionGradient.m
.....................\.....................\.......\allActionMatrix.m
.....................\.....................\.......\approximateAdvantageTDLearning.m
.....................\.....................\.......\approximateAdvantageTDLearning.m~
.....................\.....................\.......\approximateTDLearning.m
.....................\.....................\.......\directApproximation.m
.....................\.....................\.......\discountedDistribution.m
.....................\.....................\.......\DlogPiDTheta.m
.....................\.....................\.......\DlogPiDTheta.m~
.....................\.....................\.......\drawAction.m
.....................\.....................\.......\drawFromTable.m
.....................\.....................\.......\drawNextState.m
.....................\.....................\.......\drawStartState.m
.....................\.....................\.......\episodicNaturalActorCritic.m
.....................\.....................\.......\episodicREINFORCE.m
.....................\.....................\.......\estimateAllActionMatrix.m
.....................\.....................\.......\expectedReturn.m
.....................\.....................\.......\GPOMDP.m
.....................\.....................\.......\learnThroughValueFunction.m
.....................\.....................\.......\learnValueFunction.m
.....................\.....................\.......\learnValueFunction.m~
.....................\.....................\.......\LSTDQ.m
.....................\.....................\.......\naturalActorCritic.m
.....................\.....................\.......\naturalPolicyGradient.m
.....