Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

No module named 'rlkit.torch.transformer' #6

Open
hkx888 opened this issue Jul 6, 2022 · 1 comment
Open

No module named 'rlkit.torch.transformer' #6

hkx888 opened this issue Jul 6, 2022 · 1 comment

Comments

@hkx888
Copy link

hkx888 commented Jul 6, 2022

Hi,in the file "rlkit/torch/networks.py", you use "import rlkit.torch.transformer as transformer" . But it seem like the repo doesn't have rlkit.torch.transformer

@LanqingLi1993
Copy link
Owner

LanqingLi1993 commented Jul 6, 2022

Hi,

The transformer module was reserved for the follow-up paper: https://arxiv.org/pdf/2102.10774.pdf, which improves the robustness of FOCAL against sparse reward and distribution shift. For reproducing FOCAL, you can ignore that part of code.

If you are interested in applying attention/contrastive learning on FOCAL, check out the aforementioned paper (https://arxiv.org/pdf/2102.10774.pdf) and a latest follow-up paper (https://arxiv.org/pdf/2206.10442.pdf). We will have some updates on the paper and code soon. You are welcome to ask questions, too. @hkx888

Lanqing

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants