A Bayesian Model for Plan Recognition in RTS Games Applied to StarCraft

The task of keyhole (unobtrusive) plan recognition is central to adaptive game AI. "Tech trees" or "build trees" are the core of real-time strategy (RTS) game strategic (long term) planning. This paper presents a generic and simple Bayesian model for RTS build tree prediction from noisy observations, which parameters are learned from replays (game logs). This unsupervised machine learning approach involves minimal work for the game developers as it leverage players' data (common in RTS). We applied it to StarCraft1 and showed that it yields high quality and robust predictions, that can feed an adaptive AI.

[1]  Robert P. Goldman,et al.  A Bayesian Model of Plan Recognition , 1993, Artif. Intell..

[2]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[3]  Matthew J. Beal.  Variational algorithms for approximate Bayesian inference , 2003 .

[4]  Pierre Bessière,et al.  A Survey of Probabilistic Models Using the Bayesian Programming Methodology as a Unifying Framework , 2003 .

[5]  Ingrid Zukerman,et al.  Bayesian Models for Keyhole Plan Recognition in an Adventure Game , 2004, User Modeling and User-Adapted Interaction.

[6]  Pierre Bessière,et al.  Teaching Bayesian behaviours to video game characters , 2003, Robotics Auton. Syst..

[7]  M. Tribus,et al.  Probability theory: the logic of science , 2003 .

[8]  Hector Muñoz-Avila,et al.  Hierarchical Plan Representations for Encoding Strategic Game AI , 2005, AIIDE.

[9]  Jonathan Schaeffer,et al.  Monte Carlo Planning in RTS Games , 2005, CIG.

[10]  David W. Aha,et al.  Learning to Win: Case-Based Plan Selection in a Real-Time Strategy Game , 2005, Künstliche Intell..

[11]  Pieter Spronck,et al.  Opponent Modeling in Real-Time Strategy Games , 2007, GAMEON.

[12]  Santiago Ontañón,et al.  Case-Based Planning and Execution for Real-Time Strategy Games , 2007, ICCBR.

[13]  Santiago Ontañón,et al.  Situation Assessment for Plan Retrieval in Real-Time Strategy Games , 2008, ECCBR.

[14]  Christian Laugier,et al.  Probabilistic Reasoning and Decision Making in Sensory-Motor Systems , 2008, Springer Tracts in Advanced Robotics.

[15]  Santiago Ontañón,et al.  Learning from Demonstration and Case-Based Planning for Real-Time Strategy Games , 2008, Soft Computing Applications in Industry.

[16]  Chuen-Tsai Sun,et al.  Building a player strategy model by analyzing replays of real-time strategy games , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[17]  Hector Geffner,et al.  Plan Recognition as Planning , 2009, IJCAI.

[18]  Michael Mateas,et al.  A data mining approach to strategy prediction , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[19]  Robert P. Goldman,et al.  A probabilistic plan recognition algorithm based on plan tree grammars , 2009, Artif. Intell..

[20]  P. Bessière,et al.  Common Bayesian Models for Common Cognitive Issues , 2010, Acta biotheoretica.

[21]  Froduald Kabanza,et al.  Opponent Behaviour Recognition for Real-Time Strategy Games , 2010, Plan, Activity, and Intent Recognition.