Research map / Reinforcement learning / Visual and representation RL
Learning Collaborative Policies to Solve NP-hard Routing Problems
Minsu Kim, Jinkyoo Park, Joungho Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Add LCP* revision to AM | AM · TSP N=100 | cost: 7.93 -> 7.81 | Improved |
| Add LCP revision to AM | AM · PCTSP N=100 | cost: 6.07 -> 6.04 | Improved |
| Add LCP revision to AM | AM · CVRP N=100 | cost: 16.14 -> 15.98 | Improved |
| Add entropy regularization only (ablation) | AM on TSP · TSP N=100 | cost: 7.96 -> 7.96 | No clear effect |
| Add entropy regularization with weight scheduling (ablation) | AM on TSP · TSP N=100 | cost: 7.96 -> 7.94 | Improved |
| Add the reviser only (ablation) | AM on TSP · TSP N=100 | cost: 7.96 -> 7.86 | Improved |
| Add entropy regularization and reviser (ablation) | AM on TSP · TSP N=100 | cost: 7.96 -> 7.84 | Improved |
| Add entropy regularization, weight scheduling, and reviser (ablation) | AM · TSP N=100 | cost: 7.96 -> 7.82 | Improved |
| Add entropy regularization, weight scheduling, and reviser (ablation) | AM · PCTSP N=100 | cost: 6.08 -> 6.04 | Improved |
| Add entropy regularization, weight scheduling, and reviser (ablation) | AM · CVRP N=100 | cost: 16.29 -> 16.12 | Improved |
| Use linear rather than uniform entropy scaling (ablation) | LCP with alpha=0.2 · TSP N=100 | cost: 7.85 -> 7.87 | Hurt |
| Use linear rather than uniform entropy scaling (ablation) | LCP with alpha=0.5 · TSP N=100 | cost: 7.86 -> 7.84 | Improved |
Closest papers by meaning
- Reinforcement Learning for Solving the Vehicle Routing Problem (NeurIPS 2018 · similarity 0.88)
- Memory-Enhanced Neural Solvers for Routing Problems (NeurIPS 2025 · similarity 0.87)
- MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver (NeurIPS 2025 · similarity 0.86)
- Preference Optimization for Combinatorial Optimization Problems (ICML 2025 · similarity 0.85)
- DPN: Decoupling Partition and Navigation for Neural Solvers of Min-max Vehicle Routing Problems (ICML 2024 · similarity 0.85)
- INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer (ICML 2024 · similarity 0.85)
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.
