| {"mean_reward": 726.0, "std_reward": 197.54493159785193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-21T12:24:05.965546"} |
| {"mean_reward": 726.0, "std_reward": 197.54493159785193, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-01-21T12:24:05.965546"} |