• 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);
kerasrl_learner.py 19.9 KB