Thinklab-SJTU/ML4TSPBench

Official implementation of ICLR 2025 paper: "Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search".

18
/ 100
Experimental

This project offers a unified toolkit for researchers and practitioners working on the Traveling Salesman Problem (TSP) and similar complex optimization tasks. It provides a structured framework to integrate machine learning (ML) models with various search algorithms. You input raw problem data (like city coordinates for TSP), and the system helps you efficiently train, test, and apply different ML-driven solvers to get optimized routes or solutions.

No commits in the last 6 months.

Use this if you are a researcher or advanced practitioner developing or evaluating new machine learning-based approaches to solve complex combinatorial optimization problems like the Traveling Salesman Problem.

Not ideal if you are simply looking for an out-of-the-box, easy-to-use solver for a standard TSP without needing to delve into its ML model components or integrate custom algorithms.

combinatorial-optimization operations-research algorithm-development route-optimization logistics-planning
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

44

Forks

Language

C

License

Last pushed

May 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Thinklab-SJTU/ML4TSPBench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.