| {"mean_reward": -0.18232632540166377, "std_reward": 0.09547472573053171, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T20:46:57.371688"} |
| {"mean_reward": -0.18232632540166377, "std_reward": 0.09547472573053171, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-01T20:46:57.371688"} |