Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints

Online optimization with multiple budget constraints is challenging since the online decisions over a short time horizon are coupled together by strict inventory constraints. The existing manually-designed algorithms cannot achieve satisfactory average performance for this setting because they often need large number of steps convergence and/or may violate In paper, we propose new machine learning (ML) assisted unrolling approach, called LAAU (Learning-Assisted Algorithm Unrolling), which unrolls agent’s decision pipeline and leverages an ML model updating Lagrangian multiplier online. For efficient training via backpropagation, derive gradients time. We also provide cost bounds two cases when data available offline collected online, respectively. Finally, present numerical results to highlight that can outperform baselines.