| {"mean_reward": 268.28352391634866, "std_reward": 16.54369247778774, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T15:24:14.989667"} |
| {"mean_reward": 268.28352391634866, "std_reward": 16.54369247778774, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-01T15:24:14.989667"} |