adaptation - Game AI for a Turn-based Strategy Game with...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Game AI for a Turn-based Strategy Game with Plan Adaptation and Ontology-based retrieval Antonio S´anchez-Ruiz Stephen Lee-Urban ? H´ector Mu˜noz-Avila ? Bel´en D´ ıaz-Agudo Pedro Gonz´alez-Calero Dep. Ingeniera del Software e Inteligencia Artificial Universidad Complutense de Madrid, Spain { antsanch } @fdi.ucm.es, { belend,pedro } @sip.ucm.es ? Dep. of Computer Science and Engineering Lehigh University, PA, USA { sml3, hem4 } @lehigh.edu Abstract In this paper we present a novel approach for developing adaptive game AI by combining case based planning tech- niques and ontological knowledge from the game environ- ment. The proposed architecture combines several compo- nents: a case-based hierarchical planner ( Repair-SHOP ), a bridge to connect and reason with Ontologies formalized in Description Logics (DLs) based languages ( OntoBridge ), a DLs reasoner ( Pellet ) and a framework to develop Case- Based Reasoning (CBR) systems (j COLIBRI ). In our ongoing work we are applying this approach to a commercial Civiliza- tion clone turn-based strategy game (CTP2) where game AI is in charge of planning the strategies for automated players. Our goal is to demonstrate that ontology-based retrieval will result in the retrieval of strategies that are easier to adapt than those plans returned by other classical retrieval mechanisms traditionally used in case-based planning. Introduction Developing game AI, i.e. the algorithms that control Non- player Characters (NPCS) in a game, is well-known to be a difficult problem. Three outstanding challenges contribute to this difficulty. First, game developers have little time allocated to develop game AI; other aspects of game de- velopment such as storyline, graphics, network connections usually take precedence. Second, the development of en- vironments, called level design, is typically done indepen- dently of the development of the game AI. Yet, game AI will be controlling NPCs running in these environments. Third, games change over time. As games are tested, the games are tweaked to improve the gaming experience of the player. This makes constructing effective game AI a moving target. In this paper we propose a novel approach for developing adaptive game AI. At the core we propose the combination of plan adaptation techniques and ontological information relating objects in the game environment. Such ontological information is readily available in many of these games and is an integral part of their design. This is particularly the case for turn-based strategy (TBS) games. In these kinds of games, two or more opponents (some possibly automated) Copyright c 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. take turns controlling each’s empire or civilization. Control- ling these civilizations involves issuing commands to units (e.g., to attack an enemy unit, to defend a location), allocat- ing resources, and constructing new units. To win, various aspects of building a civilization must be taken into account
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern