Recent advances in reinforcement learning have demonstrated the ability of machine learning models to learn complex planning and navigation tasks. In parallel, modern brain research has uncovered the mechanisms and neural representations that underlay animal behavior in similar tasks. In this project we investigate the the neural representations that emerge in a behaving simulated reinforcement learning agent that interacts with a biologically inspired task. Different mechanisms that are known from machine learning, such as working memory are studied and compared to their biological counterpart.
The project can be scaled to fit a bachelor or master level thesis, and gives the opportunity to work with both, state-of-the art machine learning tools and integrating them with insights from modern neuroscience experiments. The project will be conducted in the Python programming language. Experience in python and Tensorflow are advantageous.