notmahi / bet Goto Github PK

Thanks for your awesome work. I've been attempting to replicate your code and have encountered a specific issue.

I noticed that the data provided for the franka kitchen as well as the franka kitchen environment itself, includes only qpos (position) data but lacks qvel (velocity) data. This absence seems to lead to a situation where the videos generated from images using env.render() exhibit some degree of shakiness or trembling.

Could you please share how you managed to produce stable, tremble-free images for your video outputs? Any guidance or workaround to address this issue would be greatly appreciated.

Dear Nur Muhammad (Mahi) Shafiullah and Zichen Jeff Cui,
Thanks a lot for sharing your work into community. May I ask did you open source the asset folder for the xarm environment? Is that possible to share the folder to me? Thanks a lot!

Best regards,
Lei

Thank you for your awesome work!
However, when I tried to download the dataset( https://osf.io/983qz/), I got a permission error as follows:

Please help me.
Best wishes.

why the observation dimension of 'bet_data_release/blockpush/multimodal_push_masks.npy' is (1000, 201, 16), and how can we get the last axis 16?