CVRPTW
Introduced by Falkner et al. in Learning to Solve Vehicle Routing Problems with Time Windows through Joint Attention
Random sampled instances of the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) for 20, 50 and 100 customer nodes.
- Coordinates sampled from unit square
- demands sampled as integers from range [1, 9]
- time windows sampled with:
- ready times (TW start) as random integers in time horizon T
- due times (TW end) sampled from Normal distribution
The dataset is used as a validation and test set to evaluate machine learning based solvers for the CVRPTW. The corresponding open source sample code can be used to sample corresponding training data or additional validation and test data, also for other problem sizes.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
