| {"mean_reward": -0.2436031887307763, "std_reward": 0.12601161688476892, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-11T23:09:49.336830"} |
| {"mean_reward": -0.2436031887307763, "std_reward": 0.12601161688476892, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-11T23:09:49.336830"} |