davidrd123's picture
Upload PPO LunarLander-v2 trained agent, 1st try, 1000000 steps
903abf5
{"mean_reward": 264.7656387157101, "std_reward": 19.77544206857468, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T02:26:31.720788"}