| {"mean_reward": 730.0, "std_reward": 322.56782232578627, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-19T22:41:54.849049"} |
| {"mean_reward": 730.0, "std_reward": 322.56782232578627, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-19T22:41:54.849049"} |