| {"mean_reward": 587.0, "std_reward": 118.36807001890332, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-22T15:37:38.748012"} |
| {"mean_reward": 587.0, "std_reward": 118.36807001890332, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-22T15:37:38.748012"} |