| {"mean_reward": -0.26353223733603953, "std_reward": 0.15410623079684246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-14T22:21:37.073126"} |
| {"mean_reward": -0.26353223733603953, "std_reward": 0.15410623079684246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-14T22:21:37.073126"} |