| {"mean_reward": 266.44011308675726, "std_reward": 19.39842959582483, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-18T17:57:56.138618"} |
| {"mean_reward": 266.44011308675726, "std_reward": 19.39842959582483, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-18T17:57:56.138618"} |