Honors Theses
Date of Award
Spring 5-10-2025
Document Type
Undergraduate Thesis
Department
Computer and Information Science
First Advisor
Charles Walter
Second Advisor
Joey Carlisle
Third Advisor
Yixin Chen
Relational Format
Dissertation/Thesis
Abstract
The video game I developed for my senior project lacked complex and engaging enemy artificial intelligence. The standard implementations of AI systems such as finite state machines and behavior trees felt like side-steps rather than innovative solutions. Upon seeing the 'magic' of machine learning in perfecting games such as Snake, Super Mario, and Flappy Bird, I was inspired to seek my answer in the field of evolutionary computation. However, my challenge differed in that the problem space would be defined by dynamic player strategies, making it not well-defined or static. As such, my evaluations are based on enemies exhibiting emergent behavior patterns evolved in response to player behavior. Emergent behavior in enemies was achieved through the development of Neural Networks whose outputs controlled its associated enemy and a Genetic Algorithm to evolve the weights of a genetic algorithm according to the fitness function. Fitness values and images associated with enemy behavior were documented during experimentation and used as evidence for the claims made about the project's success. Evolutionary computation has a potential future for applications in the mainstream video game market as a method to properly adapt game difficulty to player skill and increase player engagement.
Recommended Citation
Adams, Hermie H. III, "Evolving Enemy Behavior in Video Games" (2025). Honors Theses. 3276.
https://egrove.olemiss.edu/hon_thesis/3276
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.