Yuke Zhu

LGTM - as the last step, please check our contributing guidelines and run the pre-commit checks. The updated `robosuite/wrappers/data_collection_wrapper.py` code does not comply with the `black` formatter and the pre-commit...

Thanks for opening this issue. We are investigating this problem and will get back to you soon.

This has been fixed. Thank you for reporting the issue! **Update:** The new change might still cause some unstable behaviors. We are working on a more robust formulation of OSC...

Hi @cremebrule this issue seems to come from the default wipe demonstrations collected on an older version of robosuite. I think the easiest way would be to recollect and update...

Dear @PraveenElango, I am following up on this issue. Would you like to create a PR for this functionality?

Such physical behaviors tend to occur with small objects. It fundamentally ties to how the underlying physics engine (MuJoCo) deals with contact/collision. I would suggest tuning physical parameters, like solref...

We no longer support pybullet issues here. If you are interested in using libraries customized for pybullet with robosuite, you might want to take a look at [perls2](https://github.com/StanfordVL/perls2), which provides...

This is an error due to different versions of Lua. Add `unpack = unpack or table.unpack` on the top of the script, or change `unpack` to `table.unpack` will solve this...

I used a K40 to train the model. If you get Out of Memory error, try a smaller batch size or a shorter max sequence length. One possible cause of...

@JunjieHu It's hard for me to diagnose the OOM problem without more system config information. I hypothesize the error might come from the particular cuda, cudnn or torch versions that...