Get RGB and Depth Data in headless mode

[robinvetsch]

Is it possible to read out the depth information for each camera (mounted at the end effector of each manipulator) in headless mode?

I'm currently training an RL policy with 4096 robots in parallel. By activating the visualization (headless=False), the training process takes significantly longer.

[kellyguo11]

Hi there, you can try setting enable_cameras: True in the task config file, under the sim section, which should enable rendering for the cameras.