| {"mean_reward": 796.5, "std_reward": 255.02990020779916, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T17:14:25.617458"} |
| {"mean_reward": 796.5, "std_reward": 255.02990020779916, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-06T17:14:25.617458"} |