Welcome to RLPy’s documentation!¶
RLPy is a framework to conduct sequential decision making experiments. The current focus of this project lies on value-function-based reinforcement learning, specifically using linear function approximators. The project is distributed under the 3-Clause BSD License.
Important Links¶
- Official source code repository: http://github.com/rlpy/rlpy
- Bitbucket mirror: http://bitbucket.org/rlpy/rlpy
- Documentation: http://rlpy.readthedocs.org
- Issue Tracker: https://github.com/rlpy/rlpy/issues
- Download latest version: https://pypi.python.org/pypi/rlpy
- Mailing list: rlpy@mit.edu (Subscribe here)
Documentation¶
- Overview
- Acknowledgements
- Citing RLPy
- Staying Connected
- Installation
- Dependencies
- Getting Started
- Creating a New Agent
- Creating a New Representation
- Creating a New Domain
- Creating a New Policy
- Creating a Unit Test
- Python Nose
- Unit Test Guidelines
- Example: Tabular
- Frequently Asked Questions (FAQ)
- The RLPy API