[Feature Request] pytorch geometric integration
@vmoens is already working on this.
Since May 12, 2023.
Assessment
This issue has not been assessed yet.
Description
Motivation
I'm trying to create an RL agent which works with graph data structures. but when I pass the torch_geomteric Data object to TensorDict, It says
we only supports tensorclasses, tensordicts, numeric scalars and tensors. Got
Solution
I'm not really sure how these two should get compatible, but I think with their current structure, they can't be matched together. something should change in one of these.
Checklist
- I have checked that there is no similar issue in the repo (required)
- Dominant language
- Python
- Stars
- 3.6k
- Forks
- 487
- Avg merge
- 23h 50m
- Merged PRs (30d)
- 209
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from pytorch/rl
-
enhancement
-
enhancement
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
bancolombia/sentinel#23 ·
-
test md OpenCI
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
-
integration:quickjs org:external priority:backlog topic:code-interpreter topic:middleware type:feature
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
langchain-ai/deepagents#6450 ·
-
bug client
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 74/100