ppo-LunarLander-v2 / results.json
unlikezy's picture
2nd time to train without change
dfe6a5d verified
raw
history blame contribute delete
165 Bytes
{"mean_reward": 254.41386000000003, "std_reward": 16.263840453120572, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-15T10:52:34.981542"}