|
JAIST Repository >
School of Transdisciplinary Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/18467
|
| Title: | Procedural Maze Generation with Considering Difficulty from Human Players' Perspectives |
| Authors: | Fujihira, Keita
Hsueh, Chu-Hsuan
Ikeda, Kokolo |
| Keywords: | Procedural content generation
RPG
Maze
Difficulty |
| Issue Date: | 2022-08-01 |
| Publisher: | Springer, Cham |
| Magazine name: | Lecture Notes in Computer Science |
| Volume: | 13262 |
| Start page: | 165 |
| End page: | 175 |
| DOI: | 10.1007/978-3-031-11488-5_15 |
| Abstract: | In video game development, creating maps, enemies, and many other elements of game levels is one of the important process. In order to improve players' game experiences, game designers need to understand players' behavioral tendencies and create levels accordingly. Among various components of levels, this paper targets mazes and presents an automatic maze generation method with considering difficulty based on human players' tendencies. We first investigate the
tendencies using supervised learning and create a test player considering human-likeness by using the tendencies. The test player simulates human players' behaviors when playing mazes and judges difficulty according to the simulation results. Maze evaluation results of subject experiments show that our method succeeds in generating mazes where the difficulty estimated by the test player matches human players'. |
| Rights: | Copyright Springer Nature Switzerland AG 2022. Keita Fujihira, Chu-Hsuan Hsueh, and Kokolo Ikeda, Lecture Notes in Computer Science, vol 13262. Springer, Cham., 2022. The final publication is available at Springer via https://doi.org/10.1007/978-3-031-11488-5_15 |
| URI: | http://hdl.handle.net/10119/18467 |
| Material Type: | author |
| Appears in Collections: | d11-1. 会議発表論文 (Conference Papers)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| I-IKEDA-K0405-14.pdf | | 659Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
