The Past Present and Future of Artificial Neural Networks in Digital Games

Over the past 20 years, the topic of artificial neural networks has been a vibrant area of AI research, leading to new algorithms that have been used in a variety of disciplines including engineering, finance, artificial perception and control & simulation. Despite this, there has been a limited impact on the commercial games industry. This paper reviews some of the successful uses of neural networks in games and identifies the positive elements of their use, and discusses some of the factors that have deterred their use amongst game developers. Addressing these weaknesses, we outline ideas for future research that may aid game developers in producing more convincing AI, and may supplement or replace more traditional techniques.

[1]  D. Sheff,et al.  Game Over , 1993 .

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Padraig Cunningham,et al.  Creating socially interactive no-player characters: The µ-SIV system , 2003, Int. J. Intell. Games Simul..

[4]  Colin Fyfe.  Dynamic Strategy Creation and Selection Using Artificial Immune Systems , 2004, Int. J. Intell. Games Simul..

[5]  Darryl Charles.  Enhancing gameplay: challenges for articifical intelligence in digital games , 2003, DiGRA Conference.

[6]  Christopher M. Bishop,et al.  GTM: The Generative Topographic Mapping , 1998, Neural Computation.

[7]  Penelope Sweetser,et al.  Strategic decision-making with neural networks and influence maps , 2004 .

[8]  Terminal Ave. Vancouver.  Integrated Machine Learning For Behavior Modeling in Video Games , 2004 .

[9]  Quasim H. Mehdi,et al.  Neural Networks for Animating Variations in Character Behaviours , 2002, GAME-ON.

[10]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .

[11]  David L. Westbrook,et al.  Intelligent modeling of the user in interactive entertainment , 2002 .

[12]  Penelope Sweetser.  How to build neural networks for games , 2004 .

[13]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[14]  Nigel M. Allinson,et al.  Bayesian learning for self-organising maps , 1997 .

[15]  Stephen J. McGlinchey.  Learning of AI Players From Game Observation Data , 2003, GAME-ON.

[16]  Daniel Livingstone,et al.  Fast Marching and Fast Driving: Combining Off-Line Search and Reactive AI , 2003, GAME-ON.

[17]  Srdjan S. Stankovic,et al.  Ionospheric forecasting technique by artificial neural network , 1998 .

[18]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[19]  John E. Laird,et al.  Human-Level AI's Killer Application: Interactive Computer Games , 2000, AI Mag..

[20]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.