ppo-LunarLander-v2 / results.json
1aurent's picture
feat: new trained agent
96ed857
raw
history blame contribute delete
163 Bytes
{"mean_reward": 284.9415454813834, "std_reward": 16.33901732320092, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-11T14:47:46.886856"}