Theses and Dissertations - UTB/UTPA
Date of Award
12-2012
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
First Advisor
Dr. Emmett Tomai
Second Advisor
Dr. Richard Fowler
Third Advisor
Dr. Robert Schweller
Abstract
In this thesis we investigate the processes involved in learning to play a game. It was inspired by two observations about how human players learn to play. First, learning the domain is intertwined with goal pursuit. Second, games are designed to ramp up in complexity, walking players through a gradual cycle of acquiring, refining, and generalizing knowledge about the domain. This approach does not rely on traces of expert play. We created an integrated planning, learning and execution system that uses StarCraft as its domain. The planning module creates command/event groupings based on the data received. Observations of unit behavior are collected during execution and returned to the learning module which tests the generalization hypothesizes. The planner uses those test results to generate events that will pursue the goal and facilitate learning the domain. We demonstrate that this approach can efficiently learn the subtle traits of commands through multiple scenarios.
Granting Institution
University of Texas-Pan American
Comments
Copyright 2012 Zackary Gill. All Rights Reserved.
https://www.proquest.com/dissertations-theses/generalizing-agent-plans-behaviors-with-automated/docview/1312560197/se-2