| {"mean_reward": -0.21277101533487439, "std_reward": 0.11261203611791329, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-18T17:47:50.341734"} |
| {"mean_reward": -0.21277101533487439, "std_reward": 0.11261203611791329, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-18T17:47:50.341734"} |