| {"mean_reward": -0.22336721569299697, "std_reward": 0.1086471553415012, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-21T02:16:46.964507"} |
| {"mean_reward": -0.22336721569299697, "std_reward": 0.1086471553415012, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-07-21T02:16:46.964507"} |