Beyond Skill Rating: Advanced Matchmaking in Ghost Recon Online

Player satisfaction is particularly difficult to ensure in online games, due to interactions with other players. In adversarial multiplayer games, matchmaking typically consists in trying to match together players of similar skill level. However, this is usually based on a single-skill value, and assumes the only factor of “fun” is the game balance. We present a more advanced matchmaking strategy developed for Ghost Recon Online, an upcoming team-focused first-person shooter (FPS) from Ubisoft (Montreal, QC, Canada). We first show how incorporating more information about players than their raw skill can lead to more balanced matches. We also argue that balance is not the only factor that matters, and present a strategy to explicitly maximize the players' fun, taking advantage of a rich player profile that includes information about player behavior and personal preferences. Ultimately, our goal is to ask players to provide direct feedback on match quality through an in-game survey. However, because such data were not available for this study, we rely here on heuristics tailored to this specific game. Experiments on data collected during Ghost Recon Online's beta tests show that neural networks can effectively be used to predict both balance and player enjoyment.

[1]  Ruck Thawonmas,et al.  Haar Wavelets for Online-Game Player Classification with Dynamic Time Warping , 2008, J. Adv. Comput. Intell. Intell. Informatics.

[2]  Darryl Charles,et al.  Player-Centred Game Design: Player Modelling and Adaptive Digital Games , 2005 .

[3]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  Sergey I. Nikolenko,et al.  A New Bayesian Rating System for Team Competitions , 2011, ICML.

[5]  Julian Togelius,et al.  Modeling Player Experience for Content Creation , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[6]  Thomas Hofmann,et al.  TrueSkill™: A Bayesian Skill Rating System , 2007 .

[7]  Tom Minka,et al.  TrueSkillTM: A Bayesian Skill Rating System , 2006, NIPS.

[8]  R. A. Bradley,et al.  Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons , 1952 .

[9]  Ruck Thawonmas,et al.  Visualization of Online-Game Players Based on Their Action Behaviors , 2008, Int. J. Comput. Games Technol..

[10]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

[11]  Lei Zhang,et al.  A Factor-Based Model for Context-Sensitive Skill Rating Systems , 2010, 2010 22nd IEEE International Conference on Tools with Artificial Intelligence.

[12]  Rémi Coulom,et al.  Whole-History Rating: A Bayesian Rating System for Players of Time-Varying Strength , 2008, Computers and Games.

[13]  M. Glickman Parameter Estimation in Large Dynamic Paired Comparison Experiments , 1999 .

[14]  I. Sprinkhuizen-Kuyper,et al.  DIFFICULTY SCALING OF GAME AI , 2004 .

[15]  H. J. van den Herik,et al.  Opponent Modelling and Commercial Games , 2005 .

[16]  Ruck Thawonmas,et al.  Classification of Online Game Players Using Action Transition Probability and Kullback Leibler Entropy , 2007, J. Adv. Comput. Intell. Intell. Informatics.

[17]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[18]  Marius St,et al.  Rating systems with multiple factors , 2011 .

[19]  Alessandro Canossa,et al.  Defining personas in games using metrics , 2008, Future Play.

[20]  Georgios N. Yannakakis,et al.  TOWARDS OPTIMIZING ENTERTAINMENT IN COMPUTER GAMES , 2007, Appl. Artif. Intell..

[21]  Weiyun Huang,et al.  Apply Social Network Analysis and Data Mining to Dynamic Task Synthesis for Persistent MMORPG Virtual World , 2004, ICEC.

[22]  Chris Bateman,et al.  21st Century Game Design (Game Development Series) , 2005 .

[23]  Brendan J. Frey,et al.  Cumulative Distribution Networks and the Derivative-sum-product Algorithm: Models and Inference for Cumulative Distribution Functions on Graphs , 2008, J. Mach. Learn. Res..

[24]  Thomas W. Malone What makes computer games fun? (abstract only) , 1982, CHI 1982.

[25]  Satoshi Usami,et al.  INDIVIDUAL DIFFERENCES MULTIDIMENSIONAL BRADLEY-TERRY MODEL USING REVERSIBLE JUMP MARKOV CHAIN MONTE CARLO ALGORITHM , 2010 .

[26]  Julian Togelius,et al.  Towards automatic personalised content creation for racing games , 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

[27]  Tony R. Martinez,et al.  A Bradley–Terry artificial neural network model for individual ratings in group competitions , 2008, Neural Computing and Applications.

[28]  Robin Hunicke,et al.  AI for Dynamic Difficulty Adjustment in Games , 2004 .

[29]  Tom Minka,et al.  TrueSkill Through Time: Revisiting the History of Chess , 2007, NIPS.

[30]  Simon Colton,et al.  Player Classification Using a Meta-Clustering Approach , 2010, CGAMES 2010.

[31]  J. Shewchuk An Introduction to the Conjugate Gradient Method Without the Agonizing Pain , 1994 .

[32]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[33]  B. Díaz-Agudo,et al.  Matchmaking and Case-based Recommendations , 2011 .

[34]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS , 1952 .

[35]  Scott Counts,et al.  Personality Matters: Incorporating Detailed User Attributes and Preferences into the Matchmaking Process , 2007, 2007 40th Annual Hawaii International Conference on System Sciences (HICSS'07).

[36]  Thomas Gärtner,et al.  Predicting Dynamic Difficulty , 2011, NIPS.

[37]  Chih-Jen Lin,et al.  A Bayesian Approximation Method for Online Ranking , 2011, J. Mach. Learn. Res..

[38]  A. Elo The rating of chessplayers, past and present , 1978 .

[39]  M. Newman,et al.  A network-based ranking system for US college football , 2005, physics/0505169.

[40]  Melissa Federoff,et al.  Player-centred game design , 2006, CHI EA '06.

[41]  Georgios N. Yannakakis,et al.  Correlation between heart rate, electrodermal activity and player experience in first-person shooter games , 2010, Sandbox '10.

[42]  Sathyanarayan Anand,et al.  Evaluating Basketball Player Performance via Statistical Network Modeling , 2011 .

[43]  Jacob R. Lorch,et al.  Matchmaking for online games and other latency-sensitive P2P systems , 2009, SIGCOMM '09.

[44]  Thomas Gärtner,et al.  Player Modeling for Intelligent Difficulty Adjustment , 2009, LWA.

[45]  Pascal Vincent,et al.  The Manifold Tangent Classifier , 2011, NIPS.