An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User

Koichi MORIYAMA; Simón Enrique ORTIZ BRANCO; Mitsuhiro MATSUMOTO; Ken-ichi FUKUI; Satoshi KURIHARA; Masayuki NUMAO

doi:10.1587/transinf.E97.D.842

An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User

Koichi MORIYAMA, Simón Enrique ORTIZ BRANCO, Mitsuhiro MATSUMOTO, Ken-ichi FUKUI, Satoshi KURIHARA, Masayuki NUMAO

Full Text Views

0

Share
Cite this

Summary :

In standard fighting videogames, users usually prefer playing against other users rather than against machines because opponents controlled by machines are in a rut and users can memorize their behaviors after repetitive plays. On the other hand, human players adapt to each other's behaviors, which makes fighting videogames interesting. Thus, in this paper, we propose an artificial agent for a fighting videogame that can adapt to its users, allowing users to enjoy the game even when playing alone. In particular, this work focuses on combination attacks, or combos, that give great damage to the opponent. The agent treats combos independently, i.e., it is composed of a subagent for predicting combos the user executes, that for choosing combos the agent executes, and that for controlling the whole agent. Human users evaluated the agent compared to static opponents, and the agent received minimal negative ratings.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.4 pp.842-851

Publication Date: 2014/04/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.842

Type of Manuscript: PAPER

Category: Information Network

Authors

Koichi MORIYAMA
  Osaka University
Simón Enrique ORTIZ BRANCO
  Osaka University
Mitsuhiro MATSUMOTO
  Osaka University
Ken-ichi FUKUI
  Osaka University
Satoshi KURIHARA
  Osaka University
Masayuki NUMAO
  Osaka University

Keyword

entertainment computing, adapting agent, pattern matching, reinforcement learning

Cite this

Copy

Koichi MORIYAMA, Simón Enrique ORTIZ BRANCO, Mitsuhiro MATSUMOTO, Ken-ichi FUKUI, Satoshi KURIHARA, Masayuki NUMAO, "An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 4, pp. 842-851, April 2014, doi: 10.1587/transinf.E97.D.842.
Abstract: In standard fighting videogames, users usually prefer playing against other users rather than against machines because opponents controlled by machines are in a rut and users can memorize their behaviors after repetitive plays. On the other hand, human players adapt to each other's behaviors, which makes fighting videogames interesting. Thus, in this paper, we propose an artificial agent for a fighting videogame that can adapt to its users, allowing users to enjoy the game even when playing alone. In particular, this work focuses on combination attacks, or combos, that give great damage to the opponent. The agent treats combos independently, i.e., it is composed of a subagent for predicting combos the user executes, that for choosing combos the agent executes, and that for controlling the whole agent. Human users evaluated the agent compared to static opponents, and the agent received minimal negative ratings.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.842/_p

Copy

@ARTICLE{e97-d_4_842,
author={Koichi MORIYAMA, Simón Enrique ORTIZ BRANCO, Mitsuhiro MATSUMOTO, Ken-ichi FUKUI, Satoshi KURIHARA, Masayuki NUMAO, },
journal={IEICE TRANSACTIONS on Information},
title={An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User},
year={2014},
volume={E97-D},
number={4},
pages={842-851},
abstract={In standard fighting videogames, users usually prefer playing against other users rather than against machines because opponents controlled by machines are in a rut and users can memorize their behaviors after repetitive plays. On the other hand, human players adapt to each other's behaviors, which makes fighting videogames interesting. Thus, in this paper, we propose an artificial agent for a fighting videogame that can adapt to its users, allowing users to enjoy the game even when playing alone. In particular, this work focuses on combination attacks, or combos, that give great damage to the opponent. The agent treats combos independently, i.e., it is composed of a subagent for predicting combos the user executes, that for choosing combos the agent executes, and that for controlling the whole agent. Human users evaluated the agent compared to static opponents, and the agent received minimal negative ratings.},
keywords={},
doi={10.1587/transinf.E97.D.842},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User
T2 - IEICE TRANSACTIONS on Information
SP - 842
EP - 851
AU - Koichi MORIYAMA
AU - Simón Enrique ORTIZ BRANCO
AU - Mitsuhiro MATSUMOTO
AU - Ken-ichi FUKUI
AU - Satoshi KURIHARA
AU - Masayuki NUMAO
PY - 2014
DO - 10.1587/transinf.E97.D.842
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2014
AB - In standard fighting videogames, users usually prefer playing against other users rather than against machines because opponents controlled by machines are in a rut and users can memorize their behaviors after repetitive plays. On the other hand, human players adapt to each other's behaviors, which makes fighting videogames interesting. Thus, in this paper, we propose an artificial agent for a fighting videogame that can adapt to its users, allowing users to enjoy the game even when playing alone. In particular, this work focuses on combination attacks, or combos, that give great damage to the opponent. The agent treats combos independently, i.e., it is composed of a subagent for predicting combos the user executes, that for choosing combos the agent executes, and that for controlling the whole agent. Human users evaluated the agent compared to static opponents, and the agent received minimal negative ratings.
ER -