Goodhart in the Planner: Sampling-Based Control Exploits Rewards Learned from Human Preferences
원문 초록
Robots increasingly plan by searching against a reward model learned from human preferences. We measure what this search does to the true objective. On HalfCheetah and Hopper with crowd-sourced labels, and on Meta-World drawer-open and plate-slide with synthetic and blind human labels, harder MPPI search cuts true return by up to 76% while held-out label accuracy stays at 0.75-0.97; with human labels the drawer opens in 0 of 20 runs, against 10 of 10 for the cloned policy the planner starts from. The effect persists with a learned dynamics model and an image scorer. We prove that $\chi^2$-regularized MPPI at a temperature set by the scorer's error spread on the proposals is worst-case optimal, and that no gain can be certified once that spread exceeds the scorer's own. Calibrated from 100 ranked proposal pairs, this rule is the safest fix we test, keeping 86-94% of the cloned policy's return on drawer-open and plate-slide.
제출 이력
확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.
- arXiv:2611.09670v3제출 시각 미확인
- arXiv:2611.09670v2제출 시각 미확인
- arXiv:2611.09670v1제출 시각 미확인
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.