| {"mean_reward": 251.18413849999996, "std_reward": 14.53904972559563, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T23:32:17.910501"} |
| {"mean_reward": 251.18413849999996, "std_reward": 14.53904972559563, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T23:32:17.910501"} |