Highrl is a library for training robots using RL under the scheme of multi-level RL. The library has numerous features from generating random environment, training agents to generate curriculum learning schemes, or train robots in pre-defined environments.
Github repository: https://github.com/ahmedheakl/multi-level-rl-for-robotics
Check out the guide/install
section for further information, including how to install the project.
- Unified state-of-the art environment
- PEP8 compliant (unified code style)
- Documented functions and classes
- Tests, high code coverage and type hints
- Clean code
- Wrapped environment style
Note
This project is under active development.
guide/install guide/quickstart guide/configurations
envs/env envs/teacherenvdocs envs/robotenv envs/evalenv
utils/convexhull
genindex
modindex
search