Application allowing convenient experimentation in Reinforcement Learning - a Machine Learning domain.
Project goals are:
- keep adding new environments and agents as simple as possible
- provide a rich set of state-of-art algorithms and problems
- integrate with other existing Reinforcement Learning platforms
If you found this application useful please cite this work: dotRL: A platform for rapid Reinforcement Learning methods development and validation.
This project was previously hosted on Source Forge. Currently, we are in the process of creating a new version with a more structured approach (better design, unit-tests, etc.) here.