| {"mean_reward": -0.3833261474967003, "std_reward": 0.27460738643820504, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-18T11:48:22.434605"} |
| {"mean_reward": -0.3833261474967003, "std_reward": 0.27460738643820504, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-18T11:48:22.434605"} |