Adaptive Variants of Optimal Feedback Policies

04/06/2021
by   Brett T. Lopez, et al.
0

We combine adaptive control directly with optimal or near-optimal value functions to enhance stability and closed-loop performance in systems with parametric uncertainties. Leveraging the fundamental result that a value function is also a control Lyapunov function (CLF), combined with the fact that direct adaptive control can be immediately used once a CLF is known, we prove asymptotic closed-loop convergence of adaptive feedback controllers derived from optimization-based policies. Both matched and unmatched parametric variations are addressed, where the latter exploits a new technique based on adaptation rate scaling. The results may have particular resonance in machine learning for dynamical systems, where nominal feedback controllers are typically optimization-based but need to remain effective (beyond mere robustness) in the presence of significant but structured variations in parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2022

Learning Stochastic Parametric Differentiable Predictive Control Policies

The problem of synthesizing stochastic explicit model predictive control...
research
12/31/2020

Universal Adaptive Control for Uncertain Nonlinear Systems

Precise motion planning and control require accurate models which are of...
research
12/11/2019

Fundamental Entropic Laws and L_p Limitations of Feedback Systems: Implications for Machine-Learning-in-the-Loop Control

In this paper, we study the fundamental performance limitations for gene...
research
11/11/2021

Model-Based Reinforcement Learning for Stochastic Hybrid Systems

Optimal control of general nonlinear systems is a central challenge in a...
research
01/29/2018

Safety-aware Adaptive Reinforcement Learning with Applications to Brushbot Navigation

This paper presents a safety-aware learning framework that employs an ad...
research
06/18/2018

Towards Manipulability of Interactive Lagrangian Systems

This paper investigates manipulability of interactive Lagrangian systems...

Please sign up or login with your details

Forgot password? Click here to reset