| {"mean_reward": 6.5, "std_reward": 10.735455276791944, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T10:10:09.472253"} |
| {"mean_reward": 6.5, "std_reward": 10.735455276791944, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-02T10:10:09.472253"} |