PPO-LunarLander-v2 / results.json
davideaguglia's picture
Version-3-PPO-LunarLander-v2: 2e7 training steps
5d9ed59 verified
raw
history blame
No virus
165 Bytes
{"mean_reward": 294.26406040000006, "std_reward": 16.402414883483996, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-03T09:29:20.862713"}