Accelerating Quadratic Optimization with Reinforcement Learning

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 https: //berkeleyautomation. github. io/rlqp/.

Authors

• Jeffrey Ichnowski
• Paras Jain
• Bartolomeo Stellato
• Goran Banjac
• Michael Luo
• Francesco Borrelli
• Joseph E. Gonzalez University of California, Berkeley
• Ion Stoica
• Ken Goldberg University of California, Berkeley

Keywords

No keywords are indexed for this paper.