| {"mean_reward": 561.5, "std_reward": 194.12689149110693, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-06T20:52:44.875356"} |
| {"mean_reward": 561.5, "std_reward": 194.12689149110693, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-07-06T20:52:44.875356"} |