Griffin Hartz

Senior Project Advisor

Wesley Deneke

Document Type


Publication Date

Spring 2023


Horror, Gaming, AI, Neural Network


This project contains the design, development, and partial implementation of a survival horror game made in Unity engine. The highlight of the game's design is the machine learning agents used to create the game's enemy AI, developed with Unity's MLagents system. In the game, the player controls a construction worker who traveled into a sewer to pursue a missing coworker. They eventually find their way into a crumbling undercity where their coworker was trapped, and soon become hunted by the mutant monster that killed their coworker. Their goal is to escape the ruins without being preyed upon by the mutant as well. Contained are some videos covering the game environments and training of the AI, as well as the slides used to present which contain some explanation of the game design and AI training process. The game is not in a complete state, and the slides detail the roadmap for completing the game.

(Video files are available at the bottom of the page.)


Computer Science




Copying of this document in whole or in part is allowable only for scholarly purposes. It is understood, however, that any copying or publication of this document for commercial purposes, or for financial gain, shall not be allowed without the author’s written permission.





Hartz1 Capstone.MP4 (8912 kB)
Video of tutorial

Hartz2 capstone.MP4 (8068 kB)
Video of training the mutant

Hartz3 capstone.MP4 (6298 kB)
Video of moving around the main game area