# Improvement of Optimization using Learning Based Models in Mixed Integer Linear Programming Tasks

arXiv: https://arxiv.org/abs/2506.06291 · HTML: https://mlsanity.com/paper/2506.06291/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 17 May 2025.

## Builds on (most cited first, 6 of 6)

- [Solving Mixed Integer Programs Using Neural Networks](https://mlsanity.com/paper/2012.13349/) (2020)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Learning Primal Heuristics for Mixed Integer Programs](https://mlsanity.com/paper/2107.00866/) (2021)
- [Learning Coordination Policies over Heterogeneous Graphs for Human-Robot Teams via Recurrent Neural Schedule Propagation](https://mlsanity.com/paper/2301.13279/) (2023)
- [Faster Model Predictive Control via Self-Supervised Initialization Learning](https://mlsanity.com/paper/2408.03394/) (2024)
- [Warm-starting constraint generation for mixed-integer optimization: A Machine Learning approach](https://mlsanity.com/paper/2103.13074/) (2021)

## Abstract (arXiv)

Mixed Integer Linear Programs (MILPs) are essential tools for solving planning and scheduling problems across critical industries such as construction, manufacturing, and logistics. However, their widespread adoption is limited by long computational times, especially in large-scale, real-time scenarios. To address this, we present a learning-based framework that leverages Behavior Cloning (BC) and Reinforcement Learning (RL) to train Graph Neural Networks (GNNs), producing high-quality initial solutions for warm-starting MILP solvers in Multi-Agent Task Allocation and Scheduling Problems. Experimental results demonstrate that our method reduces optimization time and variance compared to traditional techniques while maintaining solution quality and feasibility.