Visualizing the strategic landscape of arbitrary games

We present Gamalyzer, a game-independent and efficient visualization of sets of play traces. Unlike previous work on game-independent visualization, we focus on sequences of game actions as opposed to sequences of game states. Action sequences directly represent players’ strategic decisions. Moreover, since game actions may already be recorded as part of games’ telemetry and metrics, Gamalyzer is easier to integrate into existing analysis toolchains than state-sequence-based visualizations. Gamalyzer displays each play trace as a vertical line, with symbols along the line indicating game events. Similar play traces (according to the Gamalyzer metric, a specialization of edit distance) are arranged together along the horizontal axis, and as traces become more and less similar to each other over time, they bend towards and away from each other. The Gamalyzer metric is also used to present only the most interestingly different traces in the visualization, with the rest grouped together under their most similar cousins. We position Gamalyzer as an ideal trace filtering and selection tool to be used in concert with a state-centric (and possibly game-specific) visualization for context. This article also provides a detailed account of the Gamalyzer metric and new advice for defining game action schema to maximize the benefits obtained from the tool, along with two detailed case studies of the Gamalyzer visualization in practice.

[1]  Padhraic Smyth,et al.  Clustering Sequences with Hidden Markov Models , 1996, NIPS.

[2]  Ben Shneiderman,et al.  LifeFlow: visualizing an overview of event sequences , 2011, CHI.

[3]  Raymond K. Wong,et al.  Adaptive Distance Measurement for Time Series Databases , 2007, DASFAA.

[4]  Mark O. Riedl,et al.  Monte-Carlo Tree Search for Simulation-based Strategy Analysis , 2019, ArXiv.

[5]  Michael Mateas,et al.  Playing with words: from intuition to evaluation of game dialogue interfaces , 2010, FDG.

[6]  Julian Togelius,et al.  The Mario AI Benchmark and Competitions , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[7]  G. W. Hughes,et al.  Minimum Prediction Residual Principle Applied to Speech Recognition , 1975 .

[8]  Pawan Sinha,et al.  A Perceptually Based Comparison of Image Similarity Metrics , 2011, Perception.

[9]  Julian Togelius,et al.  Crowdsourcing the Aesthetics of Platform Games , 2013, IEEE Transactions on Computational Intelligence and AI in Games.

[10]  Michael Mateas,et al.  Using Information Visualization to Understand Interactive Narrative: A Case Study on Façade , 2011, ICIDS.

[11]  Cláudio T. Silva,et al.  VisTrails: enabling interactive multiple-view visualizations , 2005, VIS 05. IEEE Visualization, 2005..

[12]  Gareth Schott,et al.  Understanding Player Experience Through the Use of Similarity Matrix , 2015, DiGRA Conference.

[13]  Christian Sebastian Loh,et al.  Measuring the (dis-)similarity between expert and novice behaviors as serious games analytics , 2013, Education and Information Technologies.

[14]  Charles A. Bouman,et al.  Perceptual image similarity experiments , 1998, Electronic Imaging.

[15]  Joanna Bryson,et al.  Learning from Play: Facilitating Character Design Through Genetic Programming and Human Mimicry , 2015, EPIA.

[16]  Julian Togelius,et al.  Decision Making Styles as Deviation from Rational Action: A Super Mario Case Study , 2013, AIIDE.

[17]  Michael Mateas,et al.  A game-independent play trace dissimilarity metric , 2014, FDG.

[18]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[19]  Yun-En Liu,et al.  Gameplay analysis through state projection , 2010, FDG.

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

[21]  Clark Verbrugge,et al.  An Exploration Tool for Predicting Stealthy Behaviour , 2013, AIIDE 2013.

[22]  Jason Weston,et al.  Mismatch string kernels for discriminative protein classification , 2004, Bioinform..

[23]  Ulrik Brandes,et al.  Eigensolver Methods for Progressive Multidimensional Scaling of Large Data , 2006, GD.

[24]  Esteban Walter Gonzalez Clua,et al.  Game Flux Analysis with Provenance , 2013, Advances in Computer Entertainment.

[25]  Vijaya Ramachandran,et al.  Cache-oblivious dynamic programming , 2006, SODA '06.

[26]  Julian Togelius,et al.  Imitating human playing styles in Super Mario Bros , 2013, Entertain. Comput..

[27]  Michael Mateas,et al.  Evaluating Play Trace (Dis)similarity Metrics , 2014, AIIDE.

[28]  Michael Mateas,et al.  Prom Week: Designing past the game/story dilemma , 2013, FDG.

[29]  Julian Togelius,et al.  Designer Modeling for Personalized Game Content Creation Tools , 2021, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[30]  Michael Mateas,et al.  Social Story Worlds With Comme il Faut , 2014, IEEE Transactions on Computational Intelligence and AI in Games.

[31]  Truong-Huy D. Nguyen,et al.  Glyph: Visualization Tool for Understanding Problem Solving Strategies in Puzzle Games , 2021, FDG.

[32]  James Bailey,et al.  Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance , 2010, J. Mach. Learn. Res..

[33]  Joshua McCoy,et al.  All the world's a stage: a playable model of social interaction inspired by dramaturgical analysis , 2012 .

[34]  Magy Seif El-Nasr,et al.  Visualizing and understanding players' behavior in video games: discovering patterns and supporting aggregation and comparison , 2011, SIGGRAPH 2011.

[35]  Ian Watson,et al.  Building a trace-based system for real-time strategy game traces , 2013 .

[36]  Günter Wallner,et al.  A spatiotemporal visualization approach for the analysis of gameplay data , 2012, CHI.