search menu icon-carat-right cmu-wordmark
Carnegie Mellon University

Software Engineering Institute

  1. SEI
  2. Publications
  3. Digital Library
  4. Using Machine Learning to Increase NPC Fidelity

Using Machine Learning to Increase NPC Fidelity

December 2021 • Technical Report
Dustin D. Updyke, Thomas G. Podnar, Geoffrey B. Dobson, John Yarger

The authors describe how they used machine learning (ML) modeling to create decision-making preferences for non-player characters (NPCs).

Publisher:

Software Engineering Institute
CMU/SEI Report Number

CMU/SEI-2021-TR-005

DOI (Digital Object Identifier):
DOI: 10.1184/R1/14107373
Subjects

Abstract

Experiences that seem real to players in training and exercise scenarios enhance learning. Improving the fidelity of automated non-player characters (NPCs) can increase the level of realism felt by players. In this report, we describe how we used machine learning (ML) modeling to create decision-making preferences for NPCs. In our research, we test ML solutions and confirm that NPCs can exhibit lifelike computer activity that improves over time.