東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Automated Video Game Tutorial Generation.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Automated Video Game Tutorial Generation./
Author:	Green, Michael Cerny.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
Description:	179 p.
Notes:	Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
Contained By:	Dissertations Abstracts International84-01B.
Subject:	Artificial intelligence. -
ISBN:	9798837517631

Automated Video Game Tutorial Generation.
Green, Michael Cerny.

Automated Video Game Tutorial Generation. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 179 p.

Source: Dissertations Abstracts International, Volume: 84-01, Section: B.

Thesis (Ph.D.)--New York University Tandon School of Engineering, 2022.

This item must not be sold to any third party vendors.

This thesis explores techniques for automated tutorial generation for video games using artificial intelligence. We begin with an overview of tutorials (both roles and types) as well as a review of PCG algorithms and AI frameworks used in this thesis. We introduce several tree search methods for critical mechanic discovery, i.e. finding mechanics that can be taught with tutorials. We compare the discovery methods using four games in the General Video Game Artificial Intelligence (GVG-AI) corpus (Zelda, Solarfox, Plants, and RealPortals). We then present a theory of Game Mechanic Alignment (GMA) which permits mechanic analysis in regards to systemic and agential influences. We demonstrate the utility of GMA using three well-known games (Super Mario, Minecraft, and Bioshock) and present a method of GMA estimation which we apply to a dataset of human playtraces for the research game Minidungeons 2 to show off its ability to extract personalized mechanic insight. We present a method of rapid, accurate play persona classification in Minidungeons 2 using mechanic frequencies in order to identify players using their behavior. We demonstrate how mechanics can be used to build instruction-based and demonstration-based tutorials using the AtDelfi System for GVG-AI games. We follow up with the capability to generate tutorial scenes with single-objective optimization and quality diversity using mechanics or procedural personas modeled after playstyles using the Mario AI, GVG-AI, and Minidungeons 2 frameworks. We then show how these scenes can be stitched together into larger levels/sequential scenes in Mario AI.

ISBN: 9798837517631Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Evolutionary algorithm

Automated Video Game Tutorial Generation.
LDR:02719nmm a2200373 4500 001 2349805
005 20221003074958.5
008 241004s2022 eng d
020 $a 9798837517631
035 $a (MiAaPQ)AAI29259746
035 $a AAI29259746
040 $a MiAaPQ $c MiAaPQ
100 1 $a Green, Michael Cerny. $3 3689224
245 1 0 $a Automated Video Game Tutorial Generation.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 179 p.
500 $a Source: Dissertations Abstracts International, Volume: 84-01, Section: B.
500 $a Advisor: Togelius, Julian.
502 $a Thesis (Ph.D.)--New York University Tandon School of Engineering, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a This thesis explores techniques for automated tutorial generation for video games using artificial intelligence. We begin with an overview of tutorials (both roles and types) as well as a review of PCG algorithms and AI frameworks used in this thesis. We introduce several tree search methods for critical mechanic discovery, i.e. finding mechanics that can be taught with tutorials. We compare the discovery methods using four games in the General Video Game Artificial Intelligence (GVG-AI) corpus (Zelda, Solarfox, Plants, and RealPortals). We then present a theory of Game Mechanic Alignment (GMA) which permits mechanic analysis in regards to systemic and agential influences. We demonstrate the utility of GMA using three well-known games (Super Mario, Minecraft, and Bioshock) and present a method of GMA estimation which we apply to a dataset of human playtraces for the research game Minidungeons 2 to show off its ability to extract personalized mechanic insight. We present a method of rapid, accurate play persona classification in Minidungeons 2 using mechanic frequencies in order to identify players using their behavior. We demonstrate how mechanics can be used to build instruction-based and demonstration-based tutorials using the AtDelfi System for GVG-AI games. We follow up with the capability to generate tutorial scenes with single-objective optimization and quality diversity using mechanics or procedural personas modeled after playstyles using the Mario AI, GVG-AI, and Minidungeons 2 frameworks. We then show how these scenes can be stitched together into larger levels/sequential scenes in Mario AI.
590 $a School code: 1988.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Mass communications. $3 3422380
650 4 $a Educational technology. $3 517670
650 4 $a Applied mathematics. $3 2122814
653 $a Evolutionary algorithm
653 $a Procedural content generation
653 $a Simulation
653 $a Tutorial
653 $a Video game
690 $a 0800
690 $a 0710
690 $a 0364
690 $a 0708
710 2 0 $a New York University Tandon School of Engineering. $b Computer Science and Engineering. $3 3428054
773 0 $t Dissertations Abstracts International $g 84-01B.
790 $a 1988
791 $a Ph.D.
792 $a 2022
793 $a English