NeurIPS · 2022
Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity
Advances in Neural Information Processing Systems
How do forecast errors translate into regret for MPC?
A general analysis pipeline converts perturbation bounds for finite horizon control into dynamic regret bounds for MPC. It handles prediction errors in costs, dynamics, and disturbances, and extends the analysis to constrained and nonlinear settings under suitable regularity conditions.
Research themes
Connections
From prediction error to control performance
Trust adaptation in linear quadratic control and perturbation bounds for MPC connect the quality of a forecast to the cost of acting on it. Nonlinear certification adds stability to this picture.
Cite this paper
Yiheng Lin, Yang Hu, Guannan Qu, Tongxin Li, Adam Wierman. Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity. Advances in Neural Information Processing Systems, 2022. https://papers.nips.cc/paper_files/paper/2022/hash/eadeef7c51ad86989cc3b311cb49ec89-Abstract-Conference.html
BibTeX
@inproceedings{tongxin-bounded-regret-mpc,
title = {{Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity}},
author = {Yiheng Lin and Yang Hu and Guannan Qu and Tongxin Li and Adam Wierman},
year = {2022},
booktitle = {Advances in Neural Information Processing Systems},
url = {https://papers.nips.cc/paper\_files/paper/2022/hash/eadeef7c51ad86989cc3b311cb49ec89-Abstract-Conference.html}
}
Related papers
Disentangling Linear Quadratic Control with Untrusted ML Predictions
DISC learns confidence in predictions of latent disturbance components. Competitive analysis covers linear and more general mixing functions, showing how online confidence adaptation can exploit accurate forecasts while maintaining protection against large errors.
Certifying Black-Box Policies With Stability for Nonlinear Control
Simply blending two stabilizing policies can cause instability. An adaptive confidence policy instead uses approximate model information to certify stability, with competitive guarantees under bounded nonlinearity and evaluations on Cart Pole and charging under distribution shift.
Robustness and Consistency in Linear Quadratic Control with Untrusted Predictions
A confidence parameter governs how much a linear quadratic controller trusts disturbance predictions. Competitive bounds describe the tradeoff between accurate and inaccurate advice, and a self tuning policy adapts confidence online using observed prediction quality.