| {"mean_reward": 302.46372194539873, "std_reward": 0.42032535861809817, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-26T17:39:47.951675"} |
| {"mean_reward": 302.46372194539873, "std_reward": 0.42032535861809817, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-26T17:39:47.951675"} |