Regret Bounds for Adaptive Nonlinear Control

11/26/2020
by   Nicholas M. Boffi, et al.
0

We study the problem of adaptively controlling a known discrete-time nonlinear system subject to unmodeled disturbances. We prove the first finite-time regret bounds for adaptive nonlinear control with matched uncertainty in the stochastic setting, showing that the regret suffered by certainty equivalence adaptive control, compared to an oracle controller with perfect knowledge of the unmodeled disturbances, is upper bounded by O(√(T)) in expectation. Furthermore, we show that when the input is subject to a k timestep delay, the regret degrades to O(k √(T)). Our analysis draws connections between classical stability notions in nonlinear control theory (Lyapunov stability and contraction theory) and modern regret analysis from online convex optimization. The use of stability theory allows us to analyze the challenging infinite-horizon single trajectory setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/04/2021

Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function

The exploration/exploitation trade-off is an inherent challenge in data-...
03/19/2021

Towards a Dimension-Free Understanding of Adaptive Linear Control

We study the problem of adaptive control of the linear quadratic regulat...
05/04/2021

Regret-Optimal Full-Information Control

We consider the infinite-horizon, discrete-time full-information control...
04/26/2019

Adaptive Regret of Convex and Smooth Functions

We investigate online convex optimization in changing environments, and ...
03/21/2020

Learning in Networked Control Systems

We design adaptive controller (learning rule) for a networked control sy...
06/03/2019

Robust stability of moving horizon estimation for nonlinear systems with bounded disturbances using adaptive arrival cost

In this paper, the robust stability and convergence to the true state of...
03/10/2021

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Discrete-time stochastic optimal control remains a challenging problem f...