Accelerating Quadratic Optimization with Reinforcement Learning

Understand

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.