• Ashish Gaurav's avatar
    MCTS Fixes · cb171a91
    Ashish Gaurav authored
    * 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
    cb171a91
Name
Last commit
Last update
..
trained_policies Loading commit data...
__init__.py Loading commit data...
baselines_learner.py Loading commit data...
controller_base.py Loading commit data...
kerasrl_learner.py Loading commit data...
learner_base.py Loading commit data...
manual_policy.py Loading commit data...
mcts_controller.py Loading commit data...
mcts_learner.py Loading commit data...
policy_base.py Loading commit data...
rl_controller.py Loading commit data...