| {"mean_reward": 588.0, "std_reward": 103.20368210485515, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-02-18T01:20:23.029217"} |
| {"mean_reward": 588.0, "std_reward": 103.20368210485515, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-02-18T01:20:23.029217"} |