BYU

Abstract by McKell Woodland

Personal Infomation


Presenter's Name

McKell Woodland

Degree Level

Doctorate

Co-Authors

Maria Fabiano
Sydney Thompson

Abstract Infomation


Department

Computer Science

Faculty Advisor

David Wingate

Title

Unsupervised Creation of Robust Environment Representations for Reinforcement Learning

Abstract

Reinforcement learning (RL) methods traditionally have suffered from large sample complexities, which reduces their widespread effectiveness. This is particularly true for the beginning stages of deep RL methods, where the methods must learn what the objects in an environment are in addition to what actions to take. We aim to improve the sample complexity of deep RL methods by disentangling these two tasks and by completing the first task with with unsupervised learning methods. In particular, we propose a method that embeds learned environmental representations into a deep Q-network (DQN), so that the DQN does not have to learn the environment itself. Specifically, we provide a Rainbow DQN with robust environment representations of Atari video games created through variational ladder autoencoders.