| {"mean_reward": 215.09347387748403, "std_reward": 47.57297968713852, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-21T15:14:38.669731"} |
| {"mean_reward": 215.09347387748403, "std_reward": 47.57297968713852, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-21T15:14:38.669731"} |