Release Version 1.5

Models

• Added ActorCrtic, AdvantageActorCritic and AsynchronousAdvantageActorCritic models.

• Refactored neural network model code so that forwardPropagate() and backPropagate() can be used independently. Also make the codes easier to understand.

• Made some fixes with the NeuralNetwork model.

• Added new activation functions to NeuralNetwork model: Gaussian, SiLU, Mish and BinaryStep.

Others

• Added DistributedLearning.