| {"mean_reward": -0.1870842, "std_reward": 0.09183425642079322, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-07T12:03:18.897404"} |
| {"mean_reward": -0.1870842, "std_reward": 0.09183425642079322, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-07T12:03:18.897404"} |