Accelerating Quadratic Optimization with Reinforcement Learning
Abstract
First-order methods for quadratic optimization such as OSQP are widely used for large-scale machine learning and embedded optimal control, where many related problems must be rapidly solved. These methods face two persistent challenges: manual hyperparameter tuning and convergence time to high-accuracy solutions. To address these, we explore how Reinforcement Learning (RL) can learn a policy to tune parameters to accelerate convergence. In experiments with well-known QP benchmarks we find that our RL policy, RLQP, significantly outperforms state-of-the-art QP solvers by up to 3x. RLQP generalizes surprisingly well to previously unseen problems with varying dimension and structure from different applications, including the QPLIB, Netlib LP and Maros-Meszaros problems. Code for RLQP is available at https://github.com/berkeleyautomation/rlqp.
Cite
@article{arxiv.2107.10847,
title = {Accelerating Quadratic Optimization with Reinforcement Learning},
author = {Jeffrey Ichnowski and Paras Jain and Bartolomeo Stellato and Goran Banjac and Michael Luo and Francesco Borrelli and Joseph E. Gonzalez and Ion Stoica and Ken Goldberg},
journal= {arXiv preprint arXiv:2107.10847},
year = {2021}
}
Comments
25 pages, 7 figures. Code available at https://github.com/berkeleyautomation/rlqp