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

Use of Rofunc in PyBullet for dual arm robot learning from demonstration #123

Open
AdrianPrados opened this issue Jan 15, 2025 · 3 comments
Labels
help wanted Extra attention is needed

Comments

@AdrianPrados
Copy link

Hello, good day.
We would like to use Rofunc for learning bi-manipulation tasks with our custom robot. Our model is fully developed in PyBullet. We would like to know if Rofunc can work without direct dependency on IsaacGym and if it could be modified to use PyBullet instead.
Thank you very much for your time.

@Skylark0924
Copy link
Owner

Of course. The repo is fully decoupled. The algorithms in the learning folder are independent of the simulator. If you wanna use RofuncRL, we have a template https://github.com/Skylark0924/RofuncRL-template and you can refer to https://rofunc.readthedocs.io/en/latest/tutorial/customizeRL.html

@Skylark0924 Skylark0924 added the help wanted Extra attention is needed label Jan 16, 2025
@AdrianPrados
Copy link
Author

Thank you very much for your quick response. Related to my previous question i would like to ask if all the Imitation learning methods that you mention in your GitHub main page are available or not. I can only see these two algorithms (https://github.com/Skylark0924/Rofunc/tree/main/rofunc/learning/RofuncIL). I would like to know if exist any example of how can be used them or other IL algorithms.
Thank you very much

@Skylark0924
Copy link
Owner

Oh actually the main branch just has full support for RL methods, IL methods like ACT and diffusion policy have not been updated. Will do later.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
help wanted Extra attention is needed
Projects
None yet
Development

No branches or pull requests

2 participants