| {"mean_reward": -0.2042388808913529, "std_reward": 0.09893091730663413, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-11T12:50:10.137022"} |
| {"mean_reward": -0.2042388808913529, "std_reward": 0.09893091730663413, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-11T12:50:10.137022"} |