# Description

When having agent-environment interaction, it is important to ensure
that PyTorch constructs no computational graph. Otherwise, it will keep
allocating memory for gradients and result in out-of-memory error.

This MR wraps all scripts with `torch.inference_mode()` to prevent this
issue.

## Type of change

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

## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./orbit.sh --format`
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file