PPO-LunarLander-v2-1M / results.json
fabiochiu's picture
More training steps
53a3c0d
raw
history blame contribute delete
165 Bytes
{"mean_reward": 252.35856430554895, "std_reward": 14.220739913973416, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-18T14:42:12.885515"}