ppo-LunarLander-v2 / results.json
fedorn's picture
5 million training steps
4528257
raw
history blame contribute delete
165 Bytes
{"mean_reward": 282.27451668055664, "std_reward": 17.431081831576428, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-28T12:00:38.052604"}