* Reimplemented UCT MCTS
* Fixed softmax
* Merged multiple branches into this branch, all of which should now be in master
* Added reuse of tree functionality
* Added the ability to expand nodes based on q values rather than at random
* Refactored everything, deleted non necessary MCTS classes and files, and mcts.py can evaluate newer MCTS

The high-level policy was trained without changelane maneuver but with immediatestop maneuver. Two problems remain: 1) the agent chooses changelane maneuver too frequently; 2) before the stop region, immediatestop maneuver works but was not chosen property after 2.5m the high-level policy training...