| {"mean_reward": -0.19939170675352216, "std_reward": 0.09620141790746312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-28T14:09:25.361382"} |
| {"mean_reward": -0.19939170675352216, "std_reward": 0.09620141790746312, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-28T14:09:25.361382"} |