ppo-LunarLander-v2 / results.json
juansebashr's picture
Third version of PPO LunarLander-v2 trained agent
fb7d512
raw
history blame contribute delete
165 Bytes
{"mean_reward": 270.71309338169533, "std_reward": 14.371572623945427, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-12T05:44:57.641102"}