| {"mean_reward": 32.3178433, "std_reward": 138.7185751957572, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-02T12:03:45.901906"} |
| {"mean_reward": 32.3178433, "std_reward": 138.7185751957572, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-02T12:03:45.901906"} |