davidrd123's picture
Upload PPO LunarLander-v2 trained agent, 1st try, 1000000 steps
1634785
raw
history blame
165 Bytes
{"mean_reward": 292.93352490328465, "std_reward": 16.396911599187234, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T04:52:05.915706"}