| {"mean_reward": -0.23130715377628802, "std_reward": 0.11553672024568465, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-07T12:14:12.891884"} |
| {"mean_reward": -0.23130715377628802, "std_reward": 0.11553672024568465, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-07T12:14:12.891884"} |