First implementation of PPO method with lunar lander environment. Reinforcement Learning course.

eaaa1ab over 3 years ago

164 Bytes

{"mean_reward": 238.74925233449986, "std_reward": 43.04176779704104, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-12T22:41:19.550023"}