ppo-LunarLander-v2 / results.json
amal94's picture
First LunarLander-v2 PPO model: mean_reward=251.58 +/- 13.59
7210aa6
raw
history blame
No virus
165 Bytes
{"mean_reward": 248.53061413480447, "std_reward": 15.626641358746825, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-06T17:17:50.487436"}