Research map / Learning theory and algorithms / Combinatorial and search optimization
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization
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 |
|---|---|---|---|
| combine learned DQN branching with CP branch-and-bound | TSPTW · 100 cities | Opt.: 0 -> 91 | Helped |
| combine learned DQN branching with CP branch-and-bound | TSPTW · 50 cities | Opt.: 0 -> 100 | Helped |
| add prediction caching (ablation) | BaB-DQN · TSPTW, 100 cities | Opt.: 52 -> 91 | Helped |
| add prediction caching (ablation) | BaB-DQN · TSPTW, 100 cities | Time: 20 -> 15 | Helped |
| use learned DQN branching with ILDS rather than standalone DQN | TSPTW · 100 cities | Opt.: 0 -> 90 | Helped |
| use learned PPO policy inside restart-based CP search rather than standalone PPO | TSPTW · 100 cities | Success: 21 -> 100 | Helped |
| combine DQN-guided CP search with the solver | PORT · continuous coefficients, 20 items | Opt.: 0 -> 100 | Helped |
| use RBS-PPO* | PORT · discrete coefficients, 50 items | Sol.: 1129.53 | Helped |
| use RBS-PPO* | PORT · continuous coefficients, 100 items | Sol.: 2674.96 vs 2683.55 | Mixed |
| cache repeated neural-network predictions (ablation) | BaB-DQN value selection · TSPTW, 100 cities | value-selection time: 34 milliseconds -> 0.16 milliseconds | Helped |
Closest papers by meaning
- Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization (ICML 2025 · similarity 0.89)
- Preference Optimization for Combinatorial Optimization Problems (ICML 2025 · similarity 0.89)
- Large Language Models as End-to-end Combinatorial Optimization Solvers (NeurIPS 2025 · similarity 0.89)
- Reinforcement learning with combinatorial actions for coupled restless bandits (ICLR 2025 · similarity 0.88)
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.87)
- Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization (ICML 2024 · similarity 0.87)
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.