Honors Program

Honors in Technology

Date of Award

5-2022

Thesis Professor(s)

Christopher Wallace

Thesis Professor Department

Computer and Information Sciences

Thesis Reader(s)

Phillip Pfeiffer

Abstract

Reinforcement learning algorithms have been used to create game-playing agents for various games—mostly, deterministic games such as chess, shogi, and Go. This study used Deep-Q reinforcement learning to create an agent that plays a non-deterministic card game, Cassino. This agent’s performance was compared against the performance of a Cassino mobile app. Results showed that the trained models did not perform well and had trouble training around build actions which are important in Cassino. Future research could experiment with other reinforcement learning algorithms to see if they are better at training around build actions.

Publisher

East Tennessee State University

Document Type

Honors Thesis - Open Access

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Copyright

Copyright by the authors.

Share

COinS