-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Adding DOT policy #739
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
base: main
Are you sure you want to change the base?
Adding DOT policy #739
Conversation
Hi! |
Hello @jadechoghari, is this still a draft? |
Hey, I forgot to reply publicly! DOT is ready (thanks @IliaLarchenko), but there's some work around the Lerobot training script indirectly related to DOT, which @Cadene suggested. Additionally, I'm also training the policy from scratch see: https://huggingface.co/jadechoghari/ckpt-policy-dpk/tree/main on different tasks and benchmarking them, will also do it on different decoders. :) The PR is in a very good state though, and I'll open it soon! |
What this does
This PR adds the new dot policy. before merging, i’ll compare it against existing policies to make sure everything aligns 🤗!
suggested by @Cadene