{"mean_reward": 320.0, "std_reward": 166.55329477377504, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-06T04:54:30.874567"} |
{"mean_reward": 320.0, "std_reward": 166.55329477377504, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-06T04:54:30.874567"} |