lunar-lander / results.json
catrabbitbear's picture
Trained lunar lander with 1e6 timesteps using PPO from stable-baselines3
1e8cee0
raw
history blame contribute delete
157 Bytes
{"mean_reward": 256.6506172, "std_reward": 38.49037601453702, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-17T13:43:18.114560"}