| {"mean_reward": -0.1867419321089983, "std_reward": 0.09081933533154993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-01T12:45:12.997825"} |
| {"mean_reward": -0.1867419321089983, "std_reward": 0.09081933533154993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-01T12:45:12.997825"} |