Release Version 1.11

Models

  • Added all the recurrent version of deep reinforcement learning models from the “Models” section to the “RecurrentModels” section. The models include:

    • RecurrentVanillaPolicyGradient

    • RecurrentActorCritic

    • RecurrentAdvantageActorCritic

    • RecurrentSoftActorCritic

    • RecurrentProximalPolicyOptimization

    • RecurrentProximalPolicyOptimizationClip

    • RecurrentDeepDeterministicPolicyGradient

    • RecurrentTwinDelayedDeepDeterministicPolicyGradient

    • RecurrentREINFORCE

    • RecurrentMonteCarloControl

    • RecurrentOffPolicyMonteCarloControl

    • RecurrentDeepQLearning

    • RecurrentDeepStateActionRewardStateAction

    • RecurrentDeepExpectedStateActionRewardStateAction

    • RecurrentDeepClippedDoubleQLearning

    • RecurrentDeepDoubleQLearningV1

    • RecurrentDeepDoubleQLearningV2

    • RecurrentDeepDoubleStateActionRewardStateActionV1

    • RecurrentDeepDoubleStateActionRewardStateActionV2

    • RecurrentDeepDoubleExpectedStateActionRewardStateActionV1

    • RecurrentDeepDoubleExpectedStateActionRewardStateActionV2

Containers

  • Refactored all the codes under the “Container” section.

Utilities

  • Refactored IterativeTrainingWrapper codes.

PaddingBlocks

  • Improved the first derivative tensor calculations for ConstantPadding, ReplicationPadding and ReflectionPadding.