ppo-LunarLander-v2 / results.json
mobiusmatt's picture
xtra training D:
cde5d76
raw
history blame contribute delete
163 Bytes
{"mean_reward": 290.5640821628891, "std_reward": 22.68242170704139, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-22T15:51:43.359610"}