A research team from the University of California, Princeton University and ETH Zurich proposes RLQP, an accelerated QP solver based on operator-splitting QP (OSQP) that uses deep reinforcement learning (RL) to speed up the solver’s convergence rate.

Here is a quick read: Accelerating Quadratic Optimization Up to 3x With Reinforcement Learning.

The paper Accelerating Quadratic Optimization with Reinforcement Learning is on arXiv.

Source link