mlsanityData to 14 Oct 2026

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

arXiv 2506.06291 ↗First posted 17 May 2025cs.LG cs.AI cs.MAcited by 0

Not on the map. Why?

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.

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

6 of 19 references.

References · 6

  1. 2020Solving Mixed Integer Programs Using Neural Networkscited by 182
  2. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
  3. 2021Learning Primal Heuristics for Mixed Integer Programscited by 14
  4. 2023Learning Coordination Policies over Heterogeneous Graphs for Human-Robot Teams via Recurrent Neural Schedule Propagationcited by 5
  5. 2024Faster Model Predictive Control via Self-Supervised Initialization Learningcited by 2
  6. 2021Warm-starting constraint generation for mixed-integer optimization: A Machine Learning approachcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Job Allocation using Reinforcement Learning with Graph Neural Networks
  2. 2026Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling
  3. 2025Solving the Job Shop Scheduling Problem with Graph Neural Networks: A Customizable Reinforcement Learning Environment
  4. 2025A Markov Decision Process for Variable Selection in Branch & Bound
  5. 2024Graph Neural Networks for Job Shop Scheduling Problems: A Survey
  6. 2021Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs
  7. 2025Machine Learning Algorithms for Improving Exact Classical Solvers in Mixed Integer Continuous Optimization
  8. 2025Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization