ComputerScienceMan/ppo-LunarLander-v3
114
1{"mean_reward": 258.2209079058275, "std_reward": 15.484425874582737, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-09-01T23:40:27.490717"}1{"mean_reward": 258.2209079058275, "std_reward": 15.484425874582737, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-09-01T23:40:27.490717"}