Quanyi Li

Use manager to manage re-spawn

Hi Erwin, We built the physics part of our [driving simulator](https://github.com/metadriverse/metadrive) with Bullet. We use the simulator to train RL agents with massive real-world driving data and thus the efficiency...

Bug when running nuplan_planner_tutorial.ipynb

9

### Describe the bug Hi, I am running the basic tutorial: ```nuplan_planner_tutorial.ipynb```. When running to the cell where ```main_simulation(cfg, planner)``` is called, I got some errors as follows. ``` ValueError:...

[Question] Can I have different number of objects in each sub-environment?

3

### Question Hi IsaacLab team, Thank you for this great work! I got a question about the parallel training. As far as I know, parallel training is launched by using...

Expose Native Buffers ID for OpenGL-CUDA Interoperability

7

## Description As discussed in https://discourse.panda3d.org/t/allowing-torch-tensorflow-to-directly-access-rendered-image-in-gpu/29119/7, it is possible to do interoperation between OpenGL and CUDA with native buffer ID. However, the related Python API lacks in Panda. Could you...

Sim-to-Real Franka

2

Hi Maniskill team, I noticed that the sim-to-real transfer for the pick-cube task works well for SO100. Did you try to do it on Franka arm? Would it be difficult...