Pierre TASSEL

@Abh4git comment is correct This repository is only the environment. You can either use our approach or define your own algorithm (RL or even another type works, too)

Hello, Sorry for the late answer, I recommend you to check out the issue #34 where I describe a way to extract the solution Thank you for the issue

Hi, Sorry for the late answer. Yes, this is normal; render just outputs a single image. If you want to generate a GIF, please check this piece of code: https://github.com/prosysscience/JSSEnv/blob/master/tests/test_rendering.py

Hi, Sorry for the late answer. This is a good question, or the first approach was just a prototype, but if you want a model that generalizes, training on multiple...

Hi, Sorry for the late answer. To render the solution, you can have a look to this piece of code: https://github.com/prosysscience/JSSEnv/blob/master/tests/test_rendering.py To load an instance, you can use the gym...

Same question from my side

Thanks for the answer, but if I am correct, the approach expect npy file such as the one in the `BenchDataNmpy` folder. How can I create one?

Sorry for the late reply. As of today, this is not possible to do. However, it is possible to modify the RayEnvWrapper to do such a thing by passing a...

I will have a look into that. In the meantime, you can use the updated requirements file in the Huggingface space: https://huggingface.co/spaces/pierretassel/JobShopCPRL/blob/main/requirements.txt It seems to run fine, except for the...

Commit 0166f8f should fix the issue, I added a Dockerfile so one can build and run a container. For those unfamiliar with Docker here are some useful commands: Build a...