効率的な外挿復帰のための収縮力学系模倣ポリシー
Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
収縮力学系としてポリシーを学習し、パラメータ選択に依らずロールアウトの収束を保証することで、外挿領域での効率的な復帰を実現した。
著者: Amin Abyaneh, Mahrokh G. Boroujeni, Hsiu-Chin Lin, Giancarlo Ferrari-Trecate
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Imitation learning is a data-driven approach to learning policies from expert behavior, but it is prone to unreliable outcomes in out-of-sample (OOS) regions. While previous research relying on stable dynamical systems guarantees convergence to a desired state, it often overlooks transient behavior. We propose a framework for learning policies modeled by contractive dynamical systems, ensuring that all policy rollouts converge regardless of perturbations, and in turn, enable efficient OOS recovery. By leveraging recurrent equilibrium networks and coupling layers, the policy structure guarantees contractivity for any parameter choice, which facilitates unconstrained optimization. We also provide theoretical upper bounds for worst-case and expected loss to rigorously establish the reliability of our method in deployment. Empirically, we demonstrate substantial OOS performance improvements for simulated robotic manipulation and navigation tasks.
