1. 06 Feb, 2019 1 commit
    • 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
  2. 01 Feb, 2019 2 commits
  3. 31 Jan, 2019 1 commit
  4. 30 Jan, 2019 8 commits
  5. 29 Jan, 2019 1 commit
  6. 24 Jan, 2019 2 commits
    • Jae Young Lee's avatar
      Improve and Bug-fix DQNLearner and environments. · 4a9327bd
      Jae Young Lee authored
      - Added RestrictedEpsGreedyPolicy and RestrictedGreedyPolicy and use them as policy and test_policy in DQNLearner. Now, the agent never chooses the action corresponding to -inf Q-value if there is at least one action with finite Q-value (if not, it chooses any action randomly, which is necessary for compatibility with keras-rl --
       see the comments in select_action).
      
      - Now, generate_scenario in SimpleIntersectionEnv generates veh_ahead_scenario even when randomize_special_scenario = 1.
      
      - In EpisodicEnvBase, the terminal reward is by default determined by the minimum one;
      
      - Small change of initiation_condition of EpisodicEnvBase (simplified);
      4a9327bd
    • Jae Young Lee's avatar
  7. 22 Jan, 2019 1 commit
    • Jae Young Lee's avatar
      Add and train more low-level policies, train a high-level policy. · a90b4bc5
      Jae Young Lee authored
      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...
      a90b4bc5
  8. 17 Jan, 2019 1 commit
  9. 19 Nov, 2018 4 commits
  10. 18 Nov, 2018 14 commits
  11. 17 Nov, 2018 3 commits
  12. 16 Nov, 2018 2 commits