| {"mean_reward": 257.3182441, "std_reward": 15.295522691083098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-15T09:20:22.650738"} |
| {"mean_reward": 257.3182441, "std_reward": 15.295522691083098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-15T09:20:22.650738"} |