Release Version 2.7

Models

Added “mode” parameter to the KMeans’ constructor.
Added OneClassSupportVectorMachine.
KMeans now accept table of matrices instead of a single matrix for its ModelParameters.
Fixed some bugs and optimized ExpectationMaximization under the “Models” section.
Fixed a bug where these models requires an Eligibility trace object when calling episodeUpdate() and reset() functions:
- DeepQLearning
- DeepDoubleQLearningV1
- DeepDoubleQLearningV2
- DeepClippedDoubleQLearning
- DeepStateActionRewardStateAction
- DeepDoubleStateActionRewardStateActionV1
- DeepDoubleStateActionRewardStateActionV2
- DeepExpectedStateActionRewardStateAction
- DeepDoubleExpectedStateActionRewardStateActionV1
- DeepDoubleExpectedStateActionRewardStateActionV2