| {"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T19:45:55.924278"} |
| {"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-05T19:45:55.924278"} |