ppo-LunarLander-v4 / results.json
Sanjay-Papaiahgari's picture
Lunar Lander agent trained using PPO with MlpPolicy for 1e6 steps
aade21e
{"mean_reward": 281.8016586924725, "std_reward": 19.890456554695206, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-10T07:14:07.897165"}