RLlib compatible with GNNs (e.g. TF-GNN, GraphTensor) or Spektral

RLlib Configure Algorithm, Training, Evaluation, Scaling
1

Is RLlib directly compatible with GNN models (e.g. TF-GNN, GraphTensor)?
I guess not, though a support for GraphTensors would be amazing and ease the use of GNNs in RLlib.

Or does it support Spektral?

2

Hi @klausk55, We still don’t have native support for GNN frameworks in RLlib. I found some old threads that you were already part of. I am not sure if you will find them helpful, but these are the only solutions that we have found in the short term.

3

Hey @kourosh,

I work on a workaround/solution integrating TF-GNN for that purpose. I’m confident to get it to work and if so, I hope I can do a PR later this months.

4

That would be awesome. :smiley:

5

@kourosh I have implemented an example for GNN models based on TF-GNN. So far, it’s just a toy/dummy example but it shows a way how to integrate GNN models into the cosmos of RLlib.
If this is of interest for you guys, let me know and then I could do a PR.

6

This is awesome to hear. Could make a PR and assign me to asses. We are working on a new API for models and policies that we could combine with your work to validate the support for GNNs with.

7

@kourosh