Reinforcement-Learning / results.json
yDiffraction's picture
Upload PPO LunarLander-v3 trained agent
8ff91f9 verified
Raw
History Blame Contribute Delete
164 Bytes
{"mean_reward": 266.8452047519139, "std_reward": 16.124903709684975, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-07-28T13:08:27.051388"}