BYU

Abstract by McKell Stauffer

Personal Infomation


Presenter's Name

McKell Stauffer

Co-Presenters

Maria Fabiano
Sydney Vickery

Degree Level

Undergraduate

Co-Authors

None

Abstract Infomation


Department

Computer Science

Faculty Advisor

David Wingate

Title

Variational Autoencoders and Reinforcement Learning

Abstract

We research the possibilities of combining reinforcement and unsupervised deep learning methods. In particular, we are interested in creating a hierarchical combination of variational auto-encoders (VAEs), generative adversarial networks (GANs), and reinforcement learning (RL) methods. Additionally, we are interested in using a class-conditional VAE as a style transfer network. We will train our model on various Atari video game representations and hope to generalize the model to other Atari video games. Lastly, we are interested in expressing VAEs as a bilevel optimization frameworks.