lunar lander model #5, using PPO trained with learning rate 0.0005, gamma 0.995, for 1M timesteps

57e96c5 over 2 years ago

163 Bytes

{"mean_reward": 245.1183278991561, "std_reward": 56.28842471651689, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T23:03:05.581705"}