| {"mean_reward": -0.2022787706926465, "std_reward": 0.05627577302059113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-24T12:22:11.319511"} |
| {"mean_reward": -0.2022787706926465, "std_reward": 0.05627577302059113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-24T12:22:11.319511"} |