Mabwiser

-------------------------------------------------------------------------------
major:
- Update warm start logic to only warm start an arm once

minor:
- Implement fix for fitting scalers in Linear policies when variance is too small

-------------------------------------------------------------------------------
minor:
- Bug fixes in examples
- Validate tree parameters of TreeBandit to be compatible with sklearn.tree.DecisionTreeRegressor

-------------------------------------------------------------------------------
major:
- Implement vectorized functions for non-contextual policies to speed-up prediction for multiple decisions.
- Change MAB predict and predict_expectations to allow empty contexts to be specified for non-contextual policies.
- Update scaler use in Linear policies so that standard scaler can be fit directly instead of pre-trained scalers.
- Change scaler argument from pre-trained `arm_to_scaler` input to a boolean scale flag.

-------------------------------------------------------------------------------
major:
- New Algorithm: LinGreedy as a learning policy.
- Thanks to Yevgeny Popkov for suggesting this algorithm.

-------------------------------------------------------------------------------

-------------------------------------------------------------------------------
major:
- Modified `predict_expectations`, such that `predict` can use `predict_expectations` directly in all non-contextual learning policies

-------------------------------------------------------------------------------

-------------------------------------------------------------------------------
major:
- Added warm_start method to MAB, that allows untrained (cold) arms to be warm started based on features of each arm.
- Added remove_arm method to MAB to allow arms to be removed from bandit.

-------------------------------------------------------------------------------