| {"mean_reward": -0.22330758785828947, "std_reward": 0.09059735300743538, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-03T12:04:32.201917"} |
| {"mean_reward": -0.22330758785828947, "std_reward": 0.09059735300743538, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-03T12:04:32.201917"} |