PPO-LunarLander-v2 / results.json
vgonisanz's picture
A new tochomodel with 5000000 steps try III
07bff78
raw
history blame contribute delete
164 Bytes
{"mean_reward": 272.6695799311336, "std_reward": 24.844293035909516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T21:40:54.760007"}