Research map / Reinforcement learning / Visual and representation RL
Reinforcement Learning for Integer Programming: Learning to Cut
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use RL to select Gomory cuts instead of the strongest baseline (LE or MNV) | Gomory cutting-plane method · Packing, 10 × 5 | cuts to optimality: 34 ± 17 -> 14 ± 11 | Helped |
| Use RL to select Gomory cuts instead of the strongest baseline (LE or MNV) | Gomory cutting-plane method · Planning, 13 × 20 | cuts to optimality: 310 ± 60 -> 10 ± 12 | Helped |
| Use RL to select Gomory cuts instead of the strongest baseline (LE or MNV) | Gomory cutting-plane method · Binary Packing, 10 × 20 | cuts to optimality: 89 ± 26 -> 22 ± 27 | Helped |
| Use RL to select Gomory cuts instead of the strongest baseline (LE or MNV) | Gomory cutting-plane method · Max Cut, 10 × 22 | cuts to optimality: 47 ± 34 -> 13 ± 4 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Packing, 30 × 30 | IGC: 0.20 ± 0.22 -> 0.55 ± 0.32 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Planning, 61 × 84 | IGC: 0.56 ± 0.16 -> 0.88 ± 0.12 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Binary Packing, 33 × 66 | IGC: 0.41 ± 0.27 -> 0.95 ± 0.14 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Max Cut, 27 × 67 | IGC: 0.62 ± 0.12 -> 0.86 ± 0.14 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Packing, 60 × 60 | IGC: 0.05 ± 0.03 -> 0.11 ± 0.05 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Planning, 121 × 168 | IGC: 0.38± 0.08 -> 0.68 ± 0.10 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Binary Packing, 66 × 132 | IGC: 0.23 ± 0.20 -> 0.61 ± 0.35 | Helped |
| Use RL to select cuts rather than the strongest heuristic baseline | Gomory cutting-plane method · Max Cut, 54 × 134 | IGC: 0.56 ± 0.11 -> 0.57 ± 0.10 | No clear effect |
Closest papers by meaning
- Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates (AAAI 2024 · similarity 0.90)
- Learning to Remove Cuts in Integer Linear Programming (ICML 2024 · similarity 0.89)
- Learning Cut Generating Functions for Integer Programming (NeurIPS 2024 · similarity 0.87)
- Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programming (AAAI 2024 · similarity 0.87)
- Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming (NeurIPS 2025 · similarity 0.86)
- LineFlow: A Framework to Learn Active Control of Production Lines (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.