| {"mean_reward": -50.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-20T14:41:16.757483"} |
| {"mean_reward": -50.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-20T14:41:16.757483"} |