| {"mean_reward": 738.0, "std_reward": 358.6377001933846, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-21T18:50:57.242485"} |
| {"mean_reward": 738.0, "std_reward": 358.6377001933846, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-21T18:50:57.242485"} |