Dissertation/Thesis Abstract

Evolving effective micro behaviors for real-time strategy games
by Liu, Siming, Ph.D., University of Nevada, Reno, 2015, 106; 3707862
Abstract (Summary)

Real-Time Strategy games have become a new frontier of artificial intelligence research. Advances in real-time strategy game AI, like with chess and checkers before, will significantly advance the state of the art in AI research. This thesis aims to investigate using heuristic search algorithms to generate effective micro behaviors in combat scenarios for real-time strategy games. Macro and micro management are two key aspects of real-time strategy games. While good macro helps a player collect more resources and build more units, good micro helps a player win skirmishes against equal numbers of opponent units or win even when outnumbered. In this research, we use influence maps and potential fields as a basis representation to evolve micro behaviors. We first compare genetic algorithms against two types of hill climbers for generating competitive unit micro management. Second, we investigated the use of case-injected genetic algorithms to quickly and reliably generate high quality micro behaviors. Then we compactly encoded micro behaviors including influence maps, potential fields, and reactive control into fourteen parameters and used genetic algorithms to search for a complete micro bot, ECSLBot. We compare the performance of our ECSLBot with two state of the art bots, UAlbertaBot and Nova, on several skirmish scenarios in a popular real-time strategy game StarCraft. The results show that the ECSLBot tuned by genetic algorithms outperforms UAlbertaBot and Nova in kiting efficiency, target selection, and fleeing. In addition, the same approach works to create competitive micro behaviors in another game SeaCraft. Using parallelized genetic algorithms to evolve parameters in SeaCraft we are able to speed up the evolutionary process from twenty one hours to nine minutes. We believe this work provides evidence that genetic algorithms and our representation may be a viable approach to creating effective micro behaviors for winning skirmishes in real-time strategy games.

Indexing (document details)
Advisor: Louis, Sushil
Commitee: Dailey, Larry, Dascalu, Sergiu, Nicolescu, Monica, Tian, Zong
School: University of Nevada, Reno
Department: Computer Science
School Location: United States -- Nevada
Source: DAI-B 76/10(E), Dissertation Abstracts International
Subjects: Artificial intelligence, Computer science
Keywords: Genetic algorithm, Machine learning, Micro, Real time strategy game
Publication Number: 3707862
ISBN: 978-1-321-82708-8
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy