プランナーにおけるグッドハート:サンプリングベース制御は人間選好から学習した報酬を悪用する
Goodhart in the Planner: Sampling-Based Control Exploits Rewards Learned from Human Preferences
人間の選好から学習した報酬モデルに対するMPPIやbest-of-N探索が、真の目的関数を最大76%悪化させることを実証し、スコアラ誤差に基づく温度設定のχ²正則化MPPIが最悪ケースで最適であることを証明した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Soovadeep Bakshi, Apurba Bose
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Robots increasingly choose actions by searching against a reward model learned from human preferences, in model-predictive control or best-of-$N$ selection; we measure what this does to the true objective. On HalfCheetah and Hopper with crowd-sourced labels, and on Meta-World drawer-open and plate-slide with synthetic labels and blind labels from the two authors, harder MPPI search cuts true return by up to 76%: with human labels the drawer opens in 0 of 20 runs against 10 of 10 for the cloned policy the planner starts from, while held-out label accuracy stays at 0.75-0.97. On plate-slide human labels are exploited less than synthetic ones, and on window-open search helps. True return roughly follows how far the planner's weights move from its proposals ($\sqrt{\mathrm{KL}}$) for both weighting rules we test, and best-of-$N$ with a verifier from synthetic labels falls below a single noisy action. We prove that $χ^2$-regularized MPPI at a temperature set by the scorer's error spread on the proposals is worst-case optimal, that no positive gain can be certified once that spread exceeds the scorer's own, and that an episode's return splits exactly into per-step terms, of which the guarantee covers the selection terms. Calibrated from 100 proposal pairs ranked by true return (an oracle) on start states the evaluation never uses, this rule is the safest fix we test: with each of five independent sets it succeeds in every arm run and keeps on average 86-94% of the cloned policy's return on plate-slide and drawer-open, though it is cautious where search helps. Calibration from a person's comparisons cannot detect a bias the scorer learned from that person; correcting for the pairs people cannot tell apart, or a second person, limits the damage.