Date of Award

5-31-2020

Document Type

Thesis

Degree Name

Master of Science in Data Science - (M.S.)

Department

Computer Science

First Advisor

Amy K. Hoover

Second Advisor

Usman W. Roshan

Third Advisor

Senjuti Basu Roy

Abstract

In recent years, games have been a popular test bed for AI research, and the presence of Collectible Card Games (CCGs) in that space is still increasing. One such CCG for both competitive/casual play and AI research is Hearthstone, a two-player adversarial game where players seeks to implement one of several gameplay strategies to defeat their opponent and decrease all of their Health points to zero. Although some open source simulators exist, some of their methodologies for simulated agents create opponents with a relatively low skill level. Using evolutionary algorithms, this thesis seeks to evolve agents with a higher skill level than those implemented in one such simulator, SabberStone. New benchmarks are propsed using supervised learning techniques to predict gameplay strategies from game data, and using unsupervised learning techniques to discover and visualize patterns that may be used in player modeling to differentiate gameplay strategies.

Share

COinS