| {"mean_reward": -0.2307150532491505, "std_reward": 0.13236466155579119, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T15:22:07.187545"} |
| {"mean_reward": -0.2307150532491505, "std_reward": 0.13236466155579119, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-24T15:22:07.187545"} |