| {"mean_reward": -0.3095138111151755, "std_reward": 0.1126791522544852, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T11:29:35.788671"} |
| {"mean_reward": -0.3095138111151755, "std_reward": 0.1126791522544852, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T11:29:35.788671"} |