| {"mean_reward": 553.5, "std_reward": 128.5505737054487, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-30T12:24:49.275859"} |
| {"mean_reward": 553.5, "std_reward": 128.5505737054487, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-30T12:24:49.275859"} |