安定な模倣学習のための収縮ベクトル場の学習
Learning Contracting Vector Fields For Stable Imitation Learning
サンプル軌道から漸近安定な力学系を学習する非パラメトリック手法を提案し、カーネル近似と凸最適化で平衡点や収縮性を制御、手書き模倣で有効性を示した。
著者: Vikas Sindhwani, Stephen Tu, Mohi Khansari
分類: cs.RO, cs.LG, stat.ML
原文アブストラクト
We propose a new non-parametric framework for learning incrementally stable dynamical systems x' = f(x) from a set of sampled trajectories. We construct a rich family of smooth vector fields induced by certain classes of matrix-valued kernels, whose equilibria are placed exactly at a desired set of locations and whose local contraction and curvature properties at various points can be explicitly controlled using convex optimization. With curl-free kernels, our framework may also be viewed as a mechanism to learn potential fields and gradient flows. We develop large-scale techniques using randomized kernel approximations in this context. We demonstrate our approach, called contracting vector fields (CVF), on imitation learning tasks involving complex point-to-point human handwriting motions.
