HORIZON: 回復可能性に基づく物理領域スケーリングのカリキュラム
HORIZON: Recoverability-Governed Curriculum for Physical-Domain Scaling
ロボットポリシーの堅牢性を高めるため、物理領域を段階的に拡張するカリキュラム学習手法HORIZONを提案。回復可能性を制約として、四足歩行タスクで有効性を示した。
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: Chenhao Bai, Liqin Lu, Kaijun Wang, Hui Chen, Jin-Chuan Shi, Yuyang Liu, Hao Chen, Chunhua Shen
分類: cs.RO
原文アブストラクト
Scaling robust robot policies requires more than broader randomization, because physical-domain experience must remain organized and learnable throughout training. We study when a policy can benefit from harder physics and identify recoverability as a central constraint in on-policy physical-domain scaling. In on-policy training, new dynamics are useful only insofar as they remain close enough to the current policy to generate corrective on-policy data, rather than collapsing rollouts into unrecoverable failures. Using quadruped locomotion as a physically demanding benchmark for embodied generalization, we introduce HORIZON, a checkpointed frontier curriculum that expands physical domains only within the current policy's recoverable boundary. HORIZON uses rollback and boundary refinement to govern each expansion step, turning fixed randomization into a continual process of physical-domain growth. Experiments reveal three regularities of physical-domain expansion. First, direct domain widening is uneven across physical axes and often unlearnable without staged ordering. Second, domain composition is non-monotonic, and adding more domains beyond a compact core can dilute recoverable joint samples and reduce overall robustness. Third, offline distillation of isolated experts cannot substitute for the joint interaction generated by on-policy curriculum. Together, these results frame physical-domain generalization as a continual growth problem for embodied control, with recoverability as the organizing principle for on-policy expansion.
