Log In Sign Up

Random features for adaptive nonlinear control and prediction

by   Nicholas M. Boffi, et al.

A key assumption in the theory of adaptive control for nonlinear systems is that the uncertainty of the system can be expressed in the linear span of a set of known basis functions. While this assumption leads to efficient algorithms, verifying it in practice can be difficult, particularly for complex systems. Here we leverage connections between reproducing kernel Hilbert spaces, random Fourier features, and universal approximation theory to propose a computationally tractable algorithm for both adaptive control and adaptive prediction that does not rely on a linearly parameterized unknown. Specifically, we approximate the unknown dynamics with a finite expansion in random basis functions, and provide an explicit guarantee on the number of random features needed to track a desired trajectory with high probability. Remarkably, our explicit bounds only depend polynomially on the underlying parameters of the system, allowing our proposed algorithms to efficiently scale to high-dimensional systems. We study a setting where the unknown dynamics splits into a component that can be modeled through available physical knowledge of the system and a component that lives in a reproducing kernel Hilbert space. Our algorithms simultaneously adapt over parameters for physical basis functions and random features to learn both components of the dynamics online.


page 1

page 2

page 3

page 4


Information Theoretic Regret Bounds for Online Nonlinear Control

This work studies the problem of sequential control in an unknown, nonli...

Shallow Representation is Deep: Learning Uncertainty-aware and Worst-case Random Feature Dynamics

Random features is a powerful universal function approximator that inher...

Finite Time Adaptive Stabilization of LQ Systems

Stabilization of linear systems with unknown dynamics is a canonical pro...

Balanced Reduction of Nonlinear Control Systems in Reproducing Kernel Hilbert Space

We introduce a novel data-driven order reduction method for nonlinear co...

Adaptive Learning in Cartesian Product of Reproducing Kernel Hilbert Spaces

We propose a novel adaptive learning algorithm based on iterative orthog...

Control Occupation Kernel Regression for Nonlinear Control-Affine Systems

This manuscript presents an algorithm for obtaining an approximation of ...

SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods

We present SOCKS, a data-driven stochastic optimal control toolbox based...