An evaluation of models for predicting opponent positions in first-person shooter video games

A well-known Artificial Intelligence (AI) problem in video games is designing AI-controlled humanoid characters. It is desirable for these characters to appear both skillful and believably human-like. Many games address the former objective by providing their agents with unfair advantages. Although challenging, these agents are frustrating to humans who perceive the AI to be cheating. In this paper we evaluate hidden semi-Markov models and particle filters as a means for predicting opponent positions. Our results show that these models can perform with similar or better accuracy than the average human expert in the game Counter-Strike: Source. Furthermore, the mistakes these models make are more human-like than perfect predictions.

[1]  D. Rubin.  Using the SIR algorithm to simulate posterior distributions , 1988 .

[2]  Welch Bl.  THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVED , 1947 .

[3]  Finnegan Southey,et al.  Inferring Complex Agent Motions from Partial Trajectory Observations , 2007, IJCAI.

[4]  Wolfram Burgard,et al.  Learning Motion Patterns of People for Compliant Robot Motion , 2005, Int. J. Robotics Res..

[5]  Kevin P. Murphy.  Hidden semi-Markov models ( HSMMs ) , 2002 .

[6]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[7]  Christian Bauckhage,et al.  Believability Testing and Bayesian Imitation in Interactive Computer Games , 2006, SAB.

[8]  John E. Laird,et al.  Creating Human-like Synthetic Characters with Multiple Skill Levels: A Case Study using the Soar Quakebot , 2001 .

[9]  Melissa A. Federoff,et al.  HEURISTICS AND USABILITY GUIDELINES FOR THE CREATION AND EVALUATION OF FUN IN VIDEO GAMES , 2002 .

[10]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[11]  Peta Wyeth,et al.  GameFlow: a model for evaluating player enjoyment in games , 2005, CIE.

[12]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[13]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[14]  John E. Laird,et al.  It knows what you're going to do: adding anticipation to a Quakebot , 2001, AGENTS '01.

[15]  Michael Buro,et al.  Real-Time Strategy Games: A New AI Research Challenge , 2003, IJCAI.

[16]  Drew A. Borovies.  Particle filter based tracking in a detection sparse discrete event simulation environment , 2007 .