|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/15122
|
| タイトル: | Learning Human-like Behaviors using NeuroEvolution with Statistical Penalties |
| 著者: | Phuc, Luong Huu
Kanazawa, Naoto
Ikeda, Kokolo |
| キーワード: | Human likeness
super Mario bros.
NeuroEvolution
Genetic Algorithm |
| 発行日: | 2017-08-22 |
| 出版者: | Institute of Electrical and Electronics Engineers (IEEE) |
| 誌名: | 2017 IEEE Conference on Computational Intelligence and Games (CIG) |
| 開始ページ: | 207 |
| 終了ページ: | 214 |
| DOI: | 10.1109/CIG.2017.8080437 |
| 抄録: | In game artificial intelligence (AI), two common directions for developing non-human computer players are strong AI and human-like AI. Human-like AI aims at making computer agents behave like humans. In this direction, NeuroEvolution (NE), which is a combination of an artificial neural network (ANN) and an evolutionary algorithm (EA), had been frequently used to a make computer agent to behave like a human. Our research introduces a novel approach to create human-like computer agents in a platform game Super Mario Bros. (SMB) - we called it a 2D action game in this research. The approach utilizes statistical penalties to evaluate candidates created by NE algorithm. The penalties help in reducing mechanical actions of computer agents based on human data statistics, and the effects of statistical penalties are analyzed by asking human subjects to rate the human-likeness of agents. Experiments show that our method improves the human-likeness in the behavior of a computer agent. |
| Rights: | This is the author's version of the work. Copyright (C) 2017 IEEE. 2017 IEEE Conference on Computational Intelligence and Games (CIG), 2017, 207-214. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/15122 |
| 資料タイプ: | author |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| 23518.pdf | | 503Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
