- A : CLinearActionContinuousTimeTransitionFunction,
CLeastSquaresLearner
- A_pinv : CLeastSquaresLearner
- action : CGraphTransition,
CStep, CGridWorldController::GridControllerRecord,
CQFunctionComperator,
CActionStatistics
- actionData : CGraphTransition,
CSampleTransition,
CStep, CAction
- actionDatas : CActionList, CActionDataSet
- actionDataSet : CQFunctionFromTransitionFunction,
CExtendedActionTransitionFunction,
CTDLearner,
CQLSTDLambda,
CPolicyGreedynessEvaluator,
CBatchLearningPolicy,
CDeterministicController
- actionDataSet2 : CAdvantageLearner
- actionFactors : CCALinearFAQETraces,
CCALinearFAQFunction
- actionGradientFeatures : CStochasticPolicy
- actionIndices : CActionList
- actionList : CEpisode
- actionProbabilities : CContinuousDynamicProgramming,
CFittedVIteration
- actionProp : CContinuousTimeAndActionTransitionFunction
- actionProperties : CContinuousActionLinearFA
- actions : CMatlabEpisodeOutputLogger,
CValueIteration,
CBatchQDataGenerator,
CActionObject
- actionSets : CActorForMultipleAgents
- actionsResource : CVPolicyLearner
- actionStack : CHierarchicalController
- actionStacks : CHierarchicalStackEpisode
- actionValues : CVFunctionFromQFunction,
CStochasticPolicy,
CContinuousActionSmoother,
CContinuousTimeAndActionSigmoidVMGradientPolicy, CContinuousTimeAndActionVMPolicy,
CContinuousActionAddController,
CContinuousActionPolicy,
CContinuousDynamicProgramming,
CActorFromQFunctionAndPolicy
- actionValues2 : CContinuousDynamicQProgramming
- actionVisitCounter : CExplorationQFunction
- actionVisits : CVisitStateActionEstimator
- activeLeaves : CForestFeatureCalculator<
TreeData >
- activePosition : CLinearMultiFeatureCalculator
- actorLearner : CFittedIteration
- actors : CActorForMultipleAgents
- actualPartition : CLinearMultiFeatureCalculator
- adaptiveGraph : CAdaptiveTargetGraphController
- adaptiveTargetGraph : CGraphAdaptiveTargetDynamicProgramming
- addToAgent : CListenerTestSuite
- agent : CTestSuiteEvaluator,
CTestSuite,
CMatlabEpisodeOutputLogger,
CNumericPolicyGradientCalculator,
CGPOMDPGradientCalculator,
CPEGASUSNumericPolicyGradientCalculator,
CPEGASUSAnalyticalPolicyGradientCalculator,
CMonteCarloError,
CPolicyEvaluator,
CFittedQNewFeatureCalculator,
CDataCollectorFromAgentLogger,
COnlinePolicyEvaluation
- agentActions : CHierarchicalController
- allActions :
CSamplingBasedTransitionModelFromTransitionFunction
- allResources : CFeatureList
- alpha : CTorchGradientFunction,
CContinuousActionSmoother,
CContinuousActionRandomPolicy,
CAdaptiveParameterFromAverageRewardCalculator
- AMatrix : CDynamicLinearContinuousTimeModel
- analyzerFile : CFittedQIterationAnalyzer
- areaNumPart : CLinearMultiFeatureCalculator
- areaSize : CLinearMultiFeatureCalculator
- attention : CSelectiveExplorationCalculator
- autoNewEpisode : CEpisode
- availableActions : COptimalVFunctionFromQFunction,
CSamplingBasedTransitionModelFromTransitionFunction,
CSampleTransition,
CStochasticPolicy,
CQGreedyPolicy,
CContinuousDynamicProgramming,
CFittedVIteration
- availableRegion : CSubGoalBehaviour
- averageError : CMatlabVAnalyzerLogger
- averageErrorFunction : CVAverageTDErrorLearner,
CQAverageTDErrorLearner
- averageReward : CAverageReinforcementBaseLineCalculator,
CAverageRewardSameStateCalculator,
CAverageRewardCalculator
- averageValue : CAverageRewardTestSuiteEvaluator,
EvaluationValue
- averageVariance : CMatlabVAnalyzerLogger
|
