| {"mean_reward": -0.19166832575574516, "std_reward": 0.11735961788063519, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-10T07:33:13.658867"} |
| {"mean_reward": -0.19166832575574516, "std_reward": 0.11735961788063519, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-10T07:33:13.658867"} |