davidrd123's picture
Upload PPO LunarLander-v2 trained agent, 1st try, 1000000 steps
8377d24
raw history blame
No virus
165 Bytes
{"mean_reward": 286.30428317564173, "std_reward": 20.547091244442004, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T04:19:23.170870"}