Camera Training Example


I’m wondering if it would be possible to include an example of training from a pixels in IsaacGym? It is currently not super straightforward to piece this together from the documentation.


Hi Arthur,

We currently do not have a training example involving pixels, but we can look into adding one in the future. Feel free to take a look at the example for how to extract camera tensors on the GPU and the rl/framework page in the docs for information on how to set up a new training task. It is also possible to extend the provided RL framework to incorporate additional functionality that you need or to hook up your own RL algorithm. Please let us know if you need additional guidance.