ac-93

Hi PaparaZz1, thanks for the kind words! Did you have anything in particular in mind or was this more of an open ended collaboration? Feel free to contact me via...

Could you point me to a PPO example with [DI-engine](https://github.com/opendilab/DI-engine) on some simple env such as cartpole? I'll try and find some time to setup something like dieng_helpers for learning...

What is it you're trying to do specifically? The json param should be in the pretrained agents that are uploaded [here](https://drive.google.com/drive/folders/1VVrnMVaQeX05C9Uo4126ATDNIPFpf2Ga). @yijionglin I think this is related to the retraining...

Thanks for the kind words! We are currently looking at the best way to release the tactile datasets and should hopefully be able to get this out soon. At the...

> I think this would be a nice fit, although I am not sure if the library you linked would work here (observations are numpy arrays up until the algorithm,...

> What you are describing applies mostly to off-policy then and could be implemented at sampling time? Yeah mostly applies to off policy, the RAD paper shows some generalization gains...

Do you have access to the mesh files (.obj, .stl, etc) for the Gelsight Mini? The way we've done this is by attaching these meshes onto a robot arm within...

Apologies, we broke some of the demos on the last update. Just did some cleanup so hopefully the demos work now. There's still some things that need fixing that I...

These issues should now be fixed. The MG400 issues came from capitalization of the STL in the mesh files, which meant that the appropriate meshes were not installed with python...