본문

서브메뉴

Efficiently Imitating Human Movement in Counter-Strike
Efficiently Imitating Human Movement in Counter-Strike
Efficiently Imitating Human Movement in Counter-Strike

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153056
ISBN  
9798346382850
DDC  
355
저자명  
Durst, David Benjamin.
서명/저자  
Efficiently Imitating Human Movement in Counter-Strike
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
106 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
주기사항  
Advisor: Fatahalian, Kayvon.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약Human-like agents have the potential to drastically improve multiplayer, first-person shooter (FPS) games. They can serve as engaging teammates, useful practice partners, and anti-social behavior detectors. However, it is difficult to create a multiplayer FPS agent that replicates human behavior, and in particular human movement. Despite game developers' efforts for decades, agents either struggle with the wide range of possible game situations in a multiplayer FPS, or are too computationally inefficient to deploy in a commercial title.This dissertation contributes a machine learning (ML)-based multiplayer FPS agent that has some of the most human-like behavior demonstrated to date while also satisfying games' performance constraints. Previous game developers avoided ML agent techniques due to the computational requirements. In order to make human-like ML tractable for real-time use in a commercial game, we made three key design decisions. First, we use an imitation learning approach to train the agent. Imitation is the most direct approach for creating human-like agents, and multiplayer FPS titles generate large datasets of demonstrations to imitate. Second, long-term human-like behavior emerges from our ML model's short-term predictions. Predicting only the next few actions enables us to automatically generate large collections of labels and utilize a simple, supervised training process. Finally, we only utilize learning where necessary. Our agent's hybrid architecture utilizes rule-based behavior generators where possible, and the ML model's game state input is in a symbolic format that can be efficiently processed.We utilize these principles to create a complete agent system. We will describe the system's four components. First, a dataset curation pipeline for creating a large-scale dataset of human movement. Second, an efficient, transformer-based movement model trained to imitate the dataset. Third, a complete agent, known as MLMove, that utilizes the learned movement model to play the multiplayer FPS game Counter-Strike. Finally, we evaluate if MLMove is human-like. Since "humanness" is difficult to evaluate, we present a suite of evaluations, including a user study and large-scale analytics, demonstrating that MLMove's behavior is more human-like than strong baselines including industry-standard and expert-crafted agents. We discuss our agent's limitations and the impact of our work on the wider field of video game agents.
일반주제명  
Defense
일반주제명  
Computer engineering
키워드  
Human-like agents
키워드  
First-person shooter games
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-06B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164866
■00520250211153056
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346382850
■035    ▼a(MiAaPQ)AAI31643418
■035    ▼a(MiAaPQ)Stanfordyz173qh1790
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a355
■1001  ▼aDurst,  David  Benjamin.
■24510▼aEfficiently  Imitating  Human  Movement  in  Counter-Strike
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a106  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-06,  Section:  B.
■500    ▼aAdvisor:  Fatahalian,  Kayvon.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aHuman-like  agents  have  the  potential  to  drastically  improve  multiplayer,  first-person  shooter  (FPS)  games.  They  can  serve  as  engaging  teammates,  useful  practice  partners,  and  anti-social  behavior  detectors.  However,  it  is  difficult  to  create  a  multiplayer  FPS  agent  that  replicates  human  behavior,  and  in  particular  human  movement.  Despite  game  developers'  efforts  for  decades,  agents  either  struggle  with  the  wide  range  of  possible  game  situations  in  a  multiplayer  FPS,  or  are  too  computationally  inefficient  to  deploy  in  a  commercial  title.This  dissertation  contributes  a  machine  learning  (ML)-based  multiplayer  FPS  agent  that  has  some  of  the  most  human-like  behavior  demonstrated  to  date  while  also  satisfying  games'  performance  constraints.  Previous  game  developers  avoided  ML  agent  techniques  due  to  the  computational  requirements.  In  order  to  make  human-like  ML  tractable  for  real-time  use  in  a  commercial  game,  we  made  three  key  design  decisions.  First,  we  use  an  imitation  learning  approach  to  train  the  agent.  Imitation  is  the  most  direct  approach  for  creating  human-like  agents,  and  multiplayer  FPS  titles  generate  large  datasets  of  demonstrations  to  imitate.  Second,  long-term  human-like  behavior  emerges  from  our  ML  model's  short-term  predictions.  Predicting  only  the  next  few  actions  enables  us  to  automatically  generate  large  collections  of  labels  and  utilize  a  simple,  supervised  training  process.  Finally,  we  only  utilize  learning  where  necessary.  Our  agent's  hybrid  architecture  utilizes  rule-based  behavior  generators  where  possible,  and  the  ML  model's  game  state  input  is  in  a  symbolic  format  that  can  be  efficiently  processed.We  utilize  these  principles  to  create  a  complete  agent  system.  We  will  describe  the  system's  four  components.  First,  a  dataset  curation  pipeline  for  creating  a  large-scale  dataset  of  human  movement.  Second,  an  efficient,  transformer-based  movement  model  trained  to  imitate  the  dataset.  Third,  a  complete  agent,  known  as  MLMove,  that  utilizes  the  learned  movement  model  to  play  the  multiplayer  FPS  game  Counter-Strike.  Finally,  we  evaluate  if  MLMove  is  human-like.  Since  "humanness"  is  difficult  to  evaluate,  we  present  a  suite  of  evaluations,  including  a  user  study  and  large-scale  analytics,  demonstrating  that  MLMove's  behavior  is  more  human-like  than  strong  baselines  including  industry-standard  and  expert-crafted  agents.  We  discuss  our  agent's  limitations  and  the  impact  of  our  work  on  the  wider  field  of  video  game  agents.
■590    ▼aSchool  code:  0212.
■650  4▼aDefense
■650  4▼aComputer  engineering
■653    ▼aHuman-like  agents
■653    ▼aFirst-person  shooter  games
■690    ▼a0464
■690    ▼a0800
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-06B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164866▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF12472 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.