English

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

Optimization and Control 2023-01-30 v2 Machine Learning

Abstract

The exploration/exploitation trade-off is an inherent challenge in data-driven adaptive control. Though this trade-off has been studied for multi-armed bandits (MAB's) and reinforcement learning for linear systems; it is less well-studied for learning-based control of nonlinear systems. A significant theoretical challenge in the nonlinear setting is that there is no explicit characterization of an optimal controller for a given set of cost and system parameters. We propose the use of a finite-horizon oracle controller with full knowledge of parameters as a reasonable surrogate to optimal controller. This allows us to develop policies in the context of learning-based MPC and MAB's and conduct a control-theoretic analysis using techniques from MPC- and optimization-theory to show these policies achieve low regret with respect to this finite-horizon oracle. Our simulations exhibit the low regret of our policy on a heating, ventilation, and air-conditioning model with partially-unknown cost function.

Keywords

Cite

@article{arxiv.2108.02307,
  title  = {Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function},
  author = {Ilgin Dogan and Zuo-Jun Max Shen and Anil Aswani},
  journal= {arXiv preprint arXiv:2108.02307},
  year   = {2023}
}

Comments

16 pages, 2 figures

R2 v1 2026-06-24T04:50:29.426Z