DeepRLCourse2022 / results.json

bguan's lunar lander model #2 using PPO trained for 500K timesteps

5498d2e over 2 years ago

164 Bytes

{"mean_reward": 218.47820877534906, "std_reward": 23.54250514950306, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-09T00:25:15.736811"}