Supervised Learning for Controlled Dynamical System Learning

develop a framework for reducing the identification of controlled dynamical systems to solving a small set of supervised learning problems. do this by adapting the two-stage regression framework proposed in (Hefny et. al. 2015) to controlled systems, which are more subtle than uncontrolled systems since they require a state representation that tolerates changes in the action policy. We then use the proposed framework to develop a non-parametric controlled system identification method that approximates the Hilbert-Space Embedding of a PSR (HSE-PSR) using random Fourier features, resulting in significant gains in learning speed. also propose an iterative procedure for improving model parameters given an initial estimate. report promising results on multiple experiments.