| {"mean_reward": 277.9090574131164, "std_reward": 16.380949293950266, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T08:07:08.446383"} |
| {"mean_reward": 277.9090574131164, "std_reward": 16.380949293950266, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-01T08:07:08.446383"} |