Beta Version 0.6.0

Added

  • Shape Transformation Blocks:

    • Permute

  • Attention Blocks:

    • BaseAttentionBlock

    • ScaledDotProductAttention

  • Deep Reinforcement Models:

    • DeepQLearning

    • DeepDoubleQLearningV1

    • DeepDoubleQLearningV2

    • DeepClippedDoubleQLearning

    • DeepStateActionRewardStateAction

    • DeepDoubleStateActionRewardStateActionV1

    • DeepDoubleStateActionRewardStateActionV2

    • DeepExpectedStateActionRewardStateAction

    • DeepDoubleExpectedStateActionRewardStateActionV1

    • DeepDoubleExpectedStateActionRewardStateActionV2

    • ActorCritic

    • AdvantageActorCritic

    • ProximalPolicyOptimization

    • ProximalPolicyOptimizationClip

    • REINFORCE

    • VanillaPolicyGradient

  • Value Schedulers:

    • BaseValueScheduler

    • TimeDecay

    • StepDecay

Changes

  • setClassesList() function and getClassesList() function are added to Sequential Container.

  • Removed “numberOfData” parameter from the BaseCostFunction’s calculateCostValue() function and calculateLossTensor() function.

  • setLearningRateScheduler() function and getLearningRateScheduler() function are added to the BaseOptimizer