Release Version 1.19

QuickSetups

• Renamed ReinforcementLearningQuickSetup to CategoricalPolicy and placed it under QuickSetups section. Also made some internal code changes.

• Added DiagonalGaussianPolicy and placed it under QuickSetups section.

Models

• ReinforcementLearningBaseModel’s and ReinforcementLearningActorCriticBaseModel’s setUpdateFunction() and update() functions have been replaced with setCategoricalUpdateFunction(), setDiagonalGaussianUpdateFunction(), categoricalUpdate() and diagonalGaussianUpdate().

• Made internal code changes to all reinforcement learning algorithms in the library.

• Made a few API breaking changes related to the AsynchronousAdvantageActorCritic model:

  • Renamed update() function to categoricalUpdate().

  • Renamed reset() function to resetAll().

  • Renamed singleReset() function to reset().

  • Added a new parameter for reinforce() function.

  • Added diagonalGaussianUpdate() function.