Rapid Adaptation of Video Game AI Rapid Adaptation of Video Game AI PROEFSCHRIFT terverkrijgingvandegraadvandoctor aandeUniversiteitvanTilburg, opgezagvanderectormagnificus, prof.dr.Ph.Eijlander, inhetopenbaarteverdedigentenoverstaanvaneen doorhetcollegevoorpromotiesaangewezencommissie indeaulavandeUniversiteit opwoensdagmaartom:uur door SanderCornelusJohannesBakkes geborenopjanuariteSwalmen Promotor: Prof.dr.H.J.vandenHerik Copromotor: Dr.ir.P.H.M.Spronck Ledenvandebeoordelingscommissie: Prof.dr.A.P.J.vandenBosch Prof.dr.J-J.Ch.Meyer Prof.dr.ir.G.vanOortmerssen Prof.dr.E.O.Postma Dr.D.W.Aha e research reported in this thesis has been funded by NWO, the Netherlands Or- ganization for Scientific Research, in the framework of the Rapid Online Learning for EntertainmentComputing(ROLEC)project,withgrantnumber... e research reported in this thesis is part of the Interactive Collaborative Information Systems(ICIS)project,supportedbytheDutchMinistryofEconomicAffairs,withgrant numberBSIK. SIKSDissertationSeriesNo.- e research reported in this thesis has been carried out under the auspices of SIKS, the DutchResearchSchoolforInformationandKnowledgeSystems. TiCCPh.D.SeriesNo. ISBN---- ©SanderBakkes CoverdesignbyJobPereboom,StudioKonstruktief All rights reserved. No part of this publication may be reproduced, stored in a retrie- val system, or transmitted, in any form or by any means, electronically, mechanically, photocopying,recordingorotherwise,withoutpriorpermissionoftheauthor. Preface Intheearlys,thevideo-gameindustryhasgrowntosurpasstheHollywoodmoviein- dustryinrevenues.Inrecentyears,videogaminghasbecomeamass-marketentertainment industryonaparwithTV,movies,andmusic.Modernvideogameshavebecomeincrea- singlyrealisticintheirvisualandauditorypresentation.However,theartificialintelligence (AI)ofvideogameshasnotreachedahighdegreeofrealismyet.Amajordisadvantageof currentgameAIisitsinabilitytoadaptadequatelytogamecircumstances.edisadvan- tagecanberesolvedbyendowinggameAIwithadaptivebehaviour,i.e.,theabilitytoadapt togamecircumstances,generallybymeansoflearningadequategamebehaviourwhilethe gameisinprogress. CurrentapproachestoadaptivegameAItypicallyrequirenumeroustrialstolearnef- fectivebehaviourinonlinegameplay(i.e.,gameadaptationisnotrapid).Inaddition,game developersareconcernedthatapplyingadaptivegameAImayresultinuncontrollableand unpredictablebehaviour(i.e.,gameadaptationisnotreliable).esecharacteristicsham- pertheincorporationofadaptivegameAIinactual,commerciallyreleasedvideogames.e generalgoalofourresearchistoinvestigatetowhatextentitispossibletoestablishgame AIcapableofadaptingrapidlyandreliablytogamecircumstances.Ourfindings,thatare discussedinthisthesis,maybeusedbygamedevelopersforincorporationinactualvideo games. isthesiswouldnothavebeenpossiblewithouttheassistanceandencouragementofa largegroupofpeople.Iwasmostfortunatethatmysupervisor,JaapvandenHerik,allowed me to pursue my goals and I owe many thanks to his support and commitment. I highly appreciatehiscommentsandadviseonmyscientificwritings,aswellashiseffortsinarran- gingadditionalfundingforfinalisingtheresearch.Aspecialgratitudegoesouttomydaily advisor,PieterSpronck,forsupportingmesoverydedicatedly,forhisresearchinspiration, andforthecharmhebringstoacademia. Moreover,IwouldliketothankmycolleaguesatTilburgUniversityandMaastrichtUni- versity.esupportivestaffofbothuniversitiesdeservemyappreciationfortheirhelpin manyrespects.IwouldespeciallyliketomentionPeterGeurtzfortechnicalassistancein thepast,andJokeHellemons,LeenJacobs,andDennisTantradjajafortheirongoingefforts in different areas of support. e research atmosphere that I experienced within the uni- versitywallsisonethatIhappilylookbackupon.Iconsidermyselfluckytohaveworkedin aninternationalenvironment,andsecretlyenjoyedthedailydosageofslightlyunorthodox behaviourandthoughtsthatitbroughtabout.Forthat,Iacknowledgegratefullyalldirect colleagues,androommatesovertheyears.IwouldespeciallyliketothankStevendeJong, GuillaumeChaslot,AlessandroRossi,SanderSpek,AndreasRüdel,SophiaKatrenko,and AnneBoldersfortheirongoingassistance,hospitality,andfriendship. During my research, I had the pleasure to supervise and cooperate with several stu- dents. I explicitly thank Laurens van der Blom, Philip Kerbusch, Bart Mehlkop, and Fre- derik Schadd, whose research efforts and their results have been integrated in the thesis. Inaddition,IthankTomNowellandAlexanderSeizingerfortheirgenerousassistancein developingAIfortheopen-sourceSgameenvironment. ii Preface Outwiththeacademia,Ifoundthesupportofindividualsandorganisationsforexpres- singmyselfintheformofphotographyandDJ’ing.HereIemphasisethecollectiveofphoto- graphers‘Nxtlvl’,andtheDJ’sof‘Loki’.Iacknowledgeinparticularthepersonsbehindsocial gatheringsinvarious(improvised)settings,andinthe‘Ipanema’,‘Zondag’,and‘Landbouw- belang’,forbringingtogetherthemanypeoplethatIwillmisswhenobligationswillchange mylifeafterthethesisdefence. Inconclusiontotheseacknowledgements,Iwouldliketothankfriendsfrommyhome- townSwalmenandmybrotherMilan,withwhomitwasapleasuretogrowup.Ichbedank mienleefomaveur’tmichmitgaevevanhäörwieslaeveslessedieouchopvandaagnaggeljig zin;enmieneljers,veurhäörónveurwaardelikkesjteunenvertroewe.Finalmente,gostaria deexpressaraminhafelicidadeporreceberoamordaCândida. SanderBakkes March, Contents Preface i Contents iii Introduction 1 . Games . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 . GameAI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 .. Goals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 .. Gamedevelopers’approachtogameAI . . . . . . . . . . . . . . . . 4 .. AcademicapproachtogameAI . . . . . . . . . . . . . . . . . . . . . 5 . Problemstatementandresearchquestions . . . . . . . . . . . . . . . . . . . 6 . Researchmethodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 . esisstructure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 Background 11 . Videogames . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 .. History. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 .. Gamegenres . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 .. Gamestudies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 .. Stateoftheindustry . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 . ResearchintogameAI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 .. EntertainmentandgameAI . . . . . . . . . . . . . . . . . . . . . . . 16 .. Non-adaptivegameAI . . . . . . . . . . . . . . . . . . . . . . . . . . 17 .. AdaptivegameAI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 . Chaptersummary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 IncrementaladaptivegameAI 21 . WhatisincrementaladaptivegameAI? . . . . . . . . . . . . . . . . . . . . . 22 . IncrementaladaptivegameAIwithTEAM . . . . . . . . . . . . . . . . . . . 23 .. TeamAI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 .. eTEAMadaptationmechanism . . . . . . . . . . . . . . . . . . . 24 .. TEAMvs.QuakeIIICTFteamAI . . . . . . . . . . . . . . . . . . . 27 .. DiscussionofTEAM . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 . IncrementaladaptivegameAIwithTEAM . . . . . . . . . . . . . . . . . . 32 .. eTEAMadaptationmechanism . . . . . . . . . . . . . . . . . . 32 .. TEAMvs.QUAKEIIICTFteamAI . . . . . . . . . . . . . . . . . . 33 .. DiscussionofTEAM . . . . . . . . . . . . . . . . . . . . . . . . . . 36 . Practicalapplicability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 . Chapterconclusions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 iv Contents Case-basedadaptivegameAI 41 . Whatiscase-basedadaptivegameAI? . . . . . . . . . . . . . . . . . . . . . 41 .. Case-basedreasoning . . . . . . . . . . . . . . . . . . . . . . . . . . 42 .. Approach . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 .. Contributionsandlimitationsoftheapproach . . . . . . . . . . . . . 44 . Case-basedadaptivegameAIformapadaptation . . . . . . . . . . . . . . . 45 .. Approachtomapadaptation . . . . . . . . . . . . . . . . . . . . . . 45 .. Experimentwithmapadaptation . . . . . . . . . . . . . . . . . . . . 47 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 55 . Case-basedadaptivegameAIinasimulatedgame . . . . . . . . . . . . . . . 55 .. Simulatedvideogame . . . . . . . . . . . . . . . . . . . . . . . . . . 56 .. Gatheringdomainknowledge . . . . . . . . . . . . . . . . . . . . . . 57 .. Exploitingdomainknowledge . . . . . . . . . . . . . . . . . . . . . . 59 .. Experimentswithexploitingdomainknowledge . . . . . . . . . . . 62 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 63 . Towardscase-basedadaptationinvideogames. . . . . . . . . . . . . . . . . 64 . Chaptersummary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65 eevaluationfunction 67 . Evaluationfunctions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68 .. Evaluationfunctionsinclassicgames . . . . . . . . . . . . . . . . . . 68 .. Evaluationfunctionsinvideogames . . . . . . . . . . . . . . . . . . 69 .. Establishinganevaluationfunction . . . . . . . . . . . . . . . . . . . 71 .. Exploitinggameknowledge . . . . . . . . . . . . . . . . . . . . . . . 73 . AnevaluationfunctionforSPRING . . . . . . . . . . . . . . . . . . . . . . . 73 .. egameenvironment . . . . . . . . . . . . . . . . . . . . . . . . . . 73 .. Towardsacasebaseofgameknowledge . . . . . . . . . . . . . . . . 76 .. Ourevaluationfunction . . . . . . . . . . . . . . . . . . . . . . . . . 77 .. Phaseofthegame. . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78 .. Materialstrength . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78 .. Commandersafety . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79 . Validatingtheevaluationfunction . . . . . . . . . . . . . . . . . . . . . . . . 79 .. Experimentalsetup . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 .. Twomeasuresforperformanceassessment . . . . . . . . . . . . . . 82 .. Measuredperformance . . . . . . . . . . . . . . . . . . . . . . . . . 82 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 86 . Chapterconclusions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 87 eadaptationmechanism 89 . Adaptationmechanisms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89 .. Rapidadaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 .. Reliableadaptation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 91 . AnadaptationmechanismforSPRING . . . . . . . . . . . . . . . . . . . . . 93 .. Generaladaptationprocedure . . . . . . . . . . . . . . . . . . . . . . 93 Contents v .. Gameindexing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94 .. Clusteringofobservations . . . . . . . . . . . . . . . . . . . . . . . . 94 .. InitialisationofgameAI . . . . . . . . . . . . . . . . . . . . . . . . . 95 .. Similaritymatching . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95 .. Onlinestrategyselection . . . . . . . . . . . . . . . . . . . . . . . . . 96 . Validatingtheadaptationmechanism . . . . . . . . . . . . . . . . . . . . . . 97 .. Experimentalsetup . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97 .. Performanceassessment . . . . . . . . . . . . . . . . . . . . . . . . . 101 .. Exp:Resultsofgameadaptation . . . . . . . . . . . . . . . . . . . . 101 .. Exp:Resultsofdifficultyscaling . . . . . . . . . . . . . . . . . . . . 104 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 105 . Chapterconclusions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 106 Opponentmodelling 109 . Opponentmodelling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 109 .. Opponentmodellinginclassicgames. . . . . . . . . . . . . . . . . . 110 .. Opponentmodellinginvideogames . . . . . . . . . . . . . . . . . . 111 . EstablishingopponentmodelsinSPRING . . . . . . . . . . . . . . . . . . . 113 .. Approachtoestablishingopponentmodels . . . . . . . . . . . . . . 113 .. Implementationoftheapproach . . . . . . . . . . . . . . . . . . . . 114 .. Experimentswiththeimplementation . . . . . . . . . . . . . . . . . 116 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 122 . ExploitingopponentmodelsinSPRING . . . . . . . . . . . . . . . . . . . . 123 .. Approachtoexploitingopponentmodels . . . . . . . . . . . . . . . 123 .. Anexperimentwithexploitingopponentmodels . . . . . . . . . . . 125 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 127 . Chapterconclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 127 Integratingthethreecomponents 129 . Howtointegratethethreecomponents . . . . . . . . . . . . . . . . . . . . . 129 . Incorporatingopponentmodelling . . . . . . . . . . . . . . . . . . . . . . . 130 .. Establishingopponentmodels . . . . . . . . . . . . . . . . . . . . . . 131 .. Exploitingopponentmodels . . . . . . . . . . . . . . . . . . . . . . . 132 . Experimentswithcase-basedadaptivegameAI . . . . . . . . . . . . . . . . 134 .. Experimentalsetup . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134 .. Performanceassessment . . . . . . . . . . . . . . . . . . . . . . . . . 134 .. Generatedopponentmodels. . . . . . . . . . . . . . . . . . . . . . . 135 .. Resultsofgameadaptation . . . . . . . . . . . . . . . . . . . . . . . 135 .. Discussionoftheresults . . . . . . . . . . . . . . . . . . . . . . . . . 138 . Practicalapplicability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 139 .. Scalability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 139 .. Dealingwithimperfectinformation . . . . . . . . . . . . . . . . . . 140 .. Generalisationtodifferentgames . . . . . . . . . . . . . . . . . . . . 141 .. Acceptancebygamedevelopers . . . . . . . . . . . . . . . . . . . . . 142 vi Contents . Chapterconclusions. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143 Conclusions 145 . Answerstotheresearchquestions . . . . . . . . . . . . . . . . . . . . . . . . 145 . Answertotheproblemstatement . . . . . . . . . . . . . . . . . . . . . . . . 147 . Futureresearch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148 References 151 Appendices 171 A Gameenvironments 171 A. QuakeIIICTF . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 171 A. SPRING . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 172 B FeaturesofgameobservationsinSPRING 177 C EvaluationfunctionforSPRING 179 D ParametersofstrategicbehaviourinSPRING 183 Summary 185 Samenvatting 189 Curriculumvitae 193 Publications 195 SIKSdissertationseries 197 TiCCPh.D.series 205
Description: