This code was produced as part of a mini-project for a course at EPFL entiteled "Unsupervised and Reinforcement Learning in Neural Networks". It is written entirely in MATLAB. For a better understanding of the algorithm and an overview of some results, please check out my project report.
The main functionality is implemented in the Arena.m file. Run the Arena_demo.m file to observe the learning process. Other files are mostly for plotting visualizations.