ppo-LunarLander-v2 / results.json
pkalkman's picture
New model trained on LunarLander-v2
11ba865 verified
raw
history blame contribute delete
158 Bytes
{"mean_reward": 294.9646722, "std_reward": 16.803995978747245, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-26T11:39:40.328917"}