| {"mean_reward": 579.5, "std_reward": 122.64685075451388, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-02T19:03:54.462870"} |
| {"mean_reward": 579.5, "std_reward": 122.64685075451388, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-02T19:03:54.462870"} |