Wouter Kool

Hi @shagharabbani, I think this would definitely be possible but is currently not implemented, also I'm not completely sure why you'd want that but feel free to try it!

Which version of Python are you using? I think this is related to using

Please have a look at #11, I'll copy it here: Hi, I had the same issue, and here is how I solved it: Turns out this is related to the...

Hi! Unfortunately the code for those visualizations is not in the repo. The training is logged using tensorboard logger, you can then visualize the results using tensorboard. If you want...

Hi! You could remove it from the code or you could simply set the demand to 0 for all customers (for which I suggest to retrain the model). However, if...

It should not be difficult to add it, have a look at the orienteering problem which also has a maximum length constraint (but only a single route). You should change...

Hi! Not sure if I fully understand your question but the code is set up to be general. For example for prize collecting TPS or orienteering, costs is not just...

Hi and thanks for trying the code! From the top of my head, training a single epoch with default settings should take around 5 minutes on a 1080Ti GPU. This...

Sorry this caused trouble, for people running into this please have a look at #11, I'll copy it here for reference: Hi, I had the same issue, and here is...

Hi! I guess you're talking about TSP? You can install Concorde by running `./install_concorde.sh` from the directory `problems/tsp`. Then from the root directory you can run `python -m problems.tsp.tsp_baseline concorde...