search

GFNOrg / torchgfn

GFlowNet library
https://torchgfn.readthedocs.io/en/latest/
Other
213 stars 26 forks source link

Add molecules environment #6

Open saleml opened 2 years ago

saleml commented 2 years ago

Implement the molecules environment following the current API. More functions might be needed !

danjenson commented 2 years ago

Careful with the versions here, I had some difficulty getting the original example running and here is some correspondence about resolving it from Emmanuel in an email:


Yes indeed, torch-geometric frequently gives us headaches. We had to rely on the internal API to perform certain operations, which changed since we published the code.
Are you using the package versions specified in [requirements.txt](https://github.com/GFNOrg/gflownet/blob/master/requirements.txt)?
Alternatively, I remember updating the code for Trajectory Balance because of that API change, I think if you fix the bits relevant to __slice__ in the model class you should be fine: https://github.com/GFNOrg/gflownet/blob/trajectory_balance/mols/model_block.py```

I haven't had a chance to debug yet, but posting here so we all have access to this information.
edwardjhu commented 2 years ago

Aha. @danjenson thanks for the heads-up! Did you get it to work?

I'm still looking into this. This env is more involved compared to hypergrid due to a learned proxy, a variable action space, and dependencies on outside packages.

saleml commented 2 years ago

Do you have a link @edwardjhu ? Can't the variable action space be handled with forward and backward masks ?

edwardjhu commented 2 years ago

It's not the action space per se. Emmanuel's codebase is versatile but not well-documented, and I'm having trouble understanding its structure. Do you have a better grasp of that codebase? If not, I'll sort it out over a call with Emmanuel or Moksh this week.

saleml commented 2 years ago

I've never used it !

josephdviviano commented 1 year ago

@edwardjhu -- I assume you went with Emmanuel's repo for this project. How hard was it to get going? Any learnings we could import if we wanted to implement a molecule env in this library?

edwardjhu commented 1 year ago

Hi Joseph! I was hoping to use this repo to support a paper I was a part of, and what ended up happening was Kolya did the molecule experiment for that paper instead. He might be the best person for your question!

josephdviviano commented 1 year ago

Thanks for the info!

josephdviviano commented 1 year ago

For reference - the molecule environment they ended up using for this project is here

https://github.com/GFNOrg/GFN_vs_HVI/tree/master/mols