1. 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);
    • Jae Young Lee's avatar
  2. 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...
  3. 17 Jan, 2019 1 commit
  4. 19 Nov, 2018 4 commits
  5. 18 Nov, 2018 14 commits
  6. 17 Nov, 2018 3 commits
  7. 16 Nov, 2018 2 commits