PPO LunarLander-v2 trained agent

de2709a almost 2 years ago

No virus

164 Bytes

{"mean_reward": 279.6257504534967, "std_reward": 15.723048979802508, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-09T19:28:40.426406"}