Release Version 1.10

Models

• Added ProximalPolicyOptimizationClip model.

• Added ReinforcementLearningActorCriticNeuralNetworkBaseModel model.

• Refactored the codes for ProximalPolicyOptimization, VanillaPolicyGradient, ActorCritic and AdvantageActorCritic so that it inherits from ReinforcementLearningActorCriticNeuralNetworkBaseModel.

• Episode updates now runs at the end of final reinforcement at the same episode. Previously it runs before the first reinforcement at the next episode.