Learning to Solve Mixed-Integer Nonlinear Programming with NNs and SQP Refinement

This is the complementary website for the paper "Learning to Solve Mixed-Integer Nonlinear Programming with Neural Networks and Sequential Quadratic Programming Refinement". In the paper, we propose a learning-to-optimize framework for solving parametric mixed-integer nonlinear programs arising in model predictive control and trajectory optimization. The proposed method combines neural network prediction with a sequential quadratic programming (SQP) refinement layer. We demonstrate the proposed framework on contact and trajectory optimization for a planar box-pushing example.