| {"mean_reward": 223.96513855645622, "std_reward": 69.23098541471184, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T21:58:59.105756"} |
| {"mean_reward": 223.96513855645622, "std_reward": 69.23098541471184, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T21:58:59.105756"} |