| {"mean_reward": -0.18007520269602537, "std_reward": 0.07881119642523089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-17T19:13:00.925447"} |
| {"mean_reward": -0.18007520269602537, "std_reward": 0.07881119642523089, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-17T19:13:00.925447"} |