Release Version 2.5

Models

• Added TabularQLearning, TabularStateActionRewardStateAction, TabularExpectedStateActionRewardStateAction, TabularMonteCarloControl, TabularOffPolicyMonteCarloControl and TabularReinforcementLearningBaseModel.

• Renamed MonteCarloControl to DeepMonteCarloControl.

• Renamed OffPolicyMonteCarloControl to DeepOffPolicyMonteCarloControl.

• Renamed ReinforcementLearningBaseModel to DeepReinforcementLearningBaseModel.

• Renamed ReinforcementLearningActorCriticBaseModel to DeepReinforcementLearningActorCriticBaseModel.

Others

• Splitted the Regularizer to BaseRegularizer, ElasticNet, Lasso and Ridge and placed them to “Regularizers” section.