Model-free Multiagent RL for RBC

A model-free multiagend reinforcement learning model for Reconnaissance Blind Chess (RBC)
Explore the docs »

Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Contributing
3. License
4. Contact

About The Project

The project is being carried out by Tristan Bandat as his bachelor thesis at the Johannes Kepler University in the Bachelor AI program.

The article Mastering the game of Stratego with model-free multiagent reinforcement learning[1] serves as the basis.

Reconnaissance Blind Chess (RBC) is a chess variant designed for new research in artificial intelligence (AI). RBC includes imperfect information, long-term strategy, explicit observations, and almost no common knowledge. These features appear in real-world scenarios, and challenge even state of the art algorithms.[2]

Built With

• PyCharm
• Pytorch
• Vim

Getting Started

Installation

Usage

Roadmap

See the open issues for a list of proposed features (and known issues).

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create.
Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Tristan Bandat - @TBandat - tristan.bandat@gmail.com

Project Link: https://github.com/TristanBandat/model-free-multiagent-RL-for-RBC

References

[1] Julien Perolat et al. ,Mastering the game of Stratego with model-free multiagent reinforcement learning.
Science378,990-996(2022).DOI: 10.1126/science.add4679

[2] Reconnaissance Blind Chess (RBC) by The Johns Hopkins University Applied Physics Laboratory LLC.
More information: https://rbc.jhuapl.edu/