# Description

We were incorrectly converting all numpy array data in the TiledCamera
class into uint8 type warp arrays when simulation device is set to CPU.
Some annotations like depth are float32 while segmentation data is
uint32. The correct behavior should convert to warp arrays depending on
the input data type of the numpy array.

Additionally, rlgames configs were set to cuda device by default but
were not being overridden when users specify the simulation device to
CPU through cmdline. We should propagate the device setting to the
rlgames configs so that we can run training on the same device, similar
to how RSL RL is set up.

Fixes #3526 

## Type of change

- Bug fix (non-breaking change which fixes an issue)


## Checklist

- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [x] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [x] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

<!--
As you go through the checklist above, you can mark something as done by
putting an x character in it

For example,
- [x] I have done this task
- [ ] I have not done this task
-->