Analysis of Effects of AIs and Interfaces to Players’ Enjoyment in Fighting Games

In this paper, we analyze effects of AIs and interfaces to players’ enjoyment in fighting games. There are two input interfaces in fighting games. One is finger-control interface such as the keyboard or gamepad, and the other is body-movement-control interface like Kinect. In order to have players enjoy playing fighting games in both input interfaces, AIs are need that evenly fight against their opponent human players. To implement such AIs, it is also necessary to have sufficiently strong AIs to be based upon. In this paper, first, we attempt to make a latter AI, called pAI, by combining MCTS with UCT (used in MCTS’s selection criteria), roulette selection, and rule-base. Next, based on pAI, by changing its UCT evaluation function, we develop eAI, an AI that dynamically adjusts its strength to that of its current player in the game. Finally, we analyze effects of both AIs and keyboard as well as Kinect interfaces to players’ enjoyment. The results of our experiments using FightingICE, a fighting game platform recently used in a number of game AI competitions, show that adjustment of AIs’ strength is an important factor for the player to play the game with more fun.

[1]  Jenova Chen,et al.  Flow in games (and everything else) , 2007, CACM.

[2]  Michèle Sebag,et al.  The grand challenge of computer Go , 2012, Commun. ACM.

[3]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[4]  Ruck Thawonmas,et al.  Fighting game artificial intelligence competition platform , 2013, 2013 IEEE 2nd Global Conference on Consumer Electronics (GCCE).

[5]  Kokolo Ikeda,et al.  Adaptive Fighting Game Computer Player by Switching Multiple Rule-Based Controllers , 2015, 2015 3rd International Conference on Applied Computing and Information Technology/2nd International Conference on Computational Science and Intelligence.

[6]  Peter I. Cowling,et al.  An experimental study of action selection mechanisms to create an entertaining opponent , 2015, 2015 IEEE Conference on Computational Intelligence and Games (CIG).

[7]  Jarrett Webb,et al.  Beginning Kinect Programming with the Microsoft Kinect SDK , 2012, Apress.

[8]  E. Vandewater,et al.  Linking obesity and activity level with children's television and video game use. , 2004, Journal of adolescence.

[9]  Alexander J. Smola,et al.  Introduction to Machine Learning , 2020, Machine Learning Refined.

[10]  Masayuki Numao,et al.  An Intelligent Fighting Videogame Opponent Adapting to Behavior Patterns of the User , 2014, IEICE Trans. Inf. Syst..

[11]  Günter Rudolph,et al.  Advanced Dynamic Scripting for Fighting Game AI , 2015, ICEC.

[12]  Ruck Thawonmas,et al.  Online adjustment of the AI's strength in a fighting game using the k-nearest neighbor algorithm and a game simulator , 2014, 2014 IEEE 3rd Global Conference on Consumer Electronics (GCCE).

[13]  Pujana Paliyawan,et al.  Towards universal kinect interface for fighting games , 2015, 2015 IEEE 4th Global Conference on Consumer Electronics (GCCE).