Skip to yearly menu bar Skip to main content


Accelerating Quadratic Optimization with Reinforcement Learning

Jeffrey Ichnowski · Paras Jain · Bartolomeo Stellato · Goran Banjac · Michael Luo · Francesco Borrelli · Joseph Gonzalez · Ion Stoica · Ken Goldberg

Keywords: [ Machine Learning ] [ Optimization ] [ Reinforcement Learning and Planning ]


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-M{\'e}sz{\'a}ros problems. Code, models, and videos are available at

Chat is not available.