A Python package that contains several gymnasium environments with positive definite cost functions, designed for compatibility with stable RL agents. It was initially created for the stable RL algorithms in the Stable Learning Control package but can be used with any RL agent requiring a positive definite cost function. For more information about stable RL agents see the Stable Learning Control documentation.
Please see the accompanying documentation for information on installing and using this package.
We use husky pre-commit hooks and github actions to enforce high code quality. Before contributing to this repository, please check the contribution guidelines.
Note
We used husky instead of pre-commit, which is more commonly used with Python projects. This was done because only some tools we wanted to use were possible to integrate the Please feel free to open a PR if you want to switch to pre-commit if this is no longer the case.