| {"mean_reward": -1.7, "std_reward": 1.004987562112089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-04T18:22:03.151303"} |
| {"mean_reward": -1.7, "std_reward": 1.004987562112089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-04T18:22:03.151303"} |