Quanyi Li

Sorry for the late reply and thanks for your interest. If you check the metadrive and anymal scripts, you can find that the policy dissection procedure is almost the same...

Hi, Please try `pip install panda3d-gltf==0.13`

You can apply the method to any well-trained MLP policies after training. Usually, the weights of this MLP policy can be stored locally in TF or Torch format. We then...

@hilookas Thank you for your great work! I want to try out the openVLA in the simulator as well. But I wonder why the performance in the sim is not...

> @QuanyiLi OpenVLA did 5 trials in real for each task (and there's no grid-based evals with >= 50 trials per task for Google Robot like in Simpler). Task settings...

@yxchng It takes me 15G vram for 4090, following the official instructions to use bf16.

@hutslib A simple workaround that comes to my mind is first to find all objects you need for all sub-environments. After this, the `clone` would copy this environment with all...