Challenge balancing for personalised game spaces

In this paper we propose an approach for personalising the space in which a game is played (i.e., levels) - to the end of tailoring the experienced challenge to the individual user during actual play of the game. Our approach specifically considers two design challenges, namely implicit user feedback and high risk of user abandonment. We contribute an approach that acknowledges that for effective online game personalisation, one needs to (1) offline learn a policy that is appropriate in expectation across users - to be used for initialising the online game, (2) offline learn a mapping from gameplay observations to the player experience - to be used for guiding the online game personalisation, and (3) rapidly converge to an appropriate policy for the individual user in online gameplay - employing the learned feedback model and a straightforward model of user abandonment. User studies that validate the approach to online game personalisation in the actual video game INFINITE MARIO BROS, indicate that it provides an effective basis for automatically balancing the game's challenge level to the individual human player.

[1]  Michael Mateas,et al.  Rhythm-based level generation for 2D platformers , 2009, FDG.

[2]  Kostas Karpouzis,et al.  A Game-Based Corpus for Analysing the Interplay between Game Context and Player Experience , 2011, ACII.

[3]  H. Jaap van den Herik,et al.  Rapid and Reliable Adaptation of Video Game AI , 2009, IEEE Transactions on Computational Intelligence and AI in Games.

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Georgios N. Yannakakis,et al.  Ranking vs. Preference: A Comparative Study of Self-reporting , 2011, ACII.

[6]  Pieter Spronck,et al.  Player behavioural modelling for video games , 2012, Entertain. Comput..

[7]  Sander Bakkes,et al.  Grammar-based Procedural Content Generation from Designer-provided Difficulty Curves , 2015, FDG.

[8]  Georgios N. Yannakakis,et al.  Real-Time Game Adaptation for Optimizing Player Satisfaction , 2009, IEEE Transactions on Computational Intelligence and AI in Games.

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

[10]  Marko Robnik-Sikonja,et al.  Theoretical and Empirical Analysis of ReliefF and RReliefF , 2003, Machine Learning.

[11]  J. Cacioppo,et al.  Issue involvement can increase or decrease persuasion by enhancing message-relevant cognitive responses. , 1979 .

[12]  Julian Togelius,et al.  Modeling player experience in Super Mario Bros , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[13]  Julian Togelius,et al.  The 2009 Mario AI Competition , 2010, IEEE Congress on Evolutionary Computation.

[14]  Diaz-Furlong Hector Adrian,et al.  An approach to level design using procedural content generation and difficulty curves , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).

[15]  Ching-I Teng,et al.  Customization, immersion satisfaction, and online gamer loyalty , 2010, Comput. Hum. Behav..

[16]  Julian Togelius,et al.  Search-Based Procedural Content Generation: A Taxonomy and Survey , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[17]  Julian Togelius,et al.  Towards multiobjective procedural map generation , 2010, PCGames@FDG.

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

[19]  Rafael Bidarra,et al.  Using gameplay semantics to procedurally generate player-matching game worlds , 2012, PCG@FDG.

[20]  Sander Bakkes,et al.  INVOLVING PLAYER EXPERIENCE IN DYNAMICALLY GENERATED MISSIONS AND GAME SPACES , 2010 .

[21]  Julian Togelius,et al.  Experience-Driven Procedural Content Generation , 2011, IEEE Transactions on Affective Computing.

[22]  Mark O. Riedl,et al.  A Temporal Data-Driven Player Model for Dynamic Difficulty Adjustment , 2012, AIIDE.

[23]  TU Darmstadt Hochschulstrasse.  Recent Advances in Machine Learning and Game Playing , 2007 .

[24]  William K. Darley,et al.  The effect of consumers' emotional reactions on behavioral intention: The moderating role of personal relevance and self‐monitoring , 1992 .

[25]  Julian Togelius,et al.  Active player modelling , 2013, FDG.

[26]  Sander Bakkes,et al.  Generating Missions and Spaces for Adaptable Play Experiences , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[27]  H. Jaap van den Herik,et al.  Games as personality profiling tools , 2011, 2011 IEEE Conference on Computational Intelligence and Games (CIG'11).

[28]  Julian Togelius,et al.  Making Racing Fun Through Player Modeling and Track Evolution , 2006 .

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

[30]  Philippe Pasquier,et al.  A Generic Approach to Challenge Modeling for the Procedural Creation of Video Game Levels , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[31]  Mark O. Riedl.  Scalable personalization of interactive experiences through creative automation , 2010, CIE.

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

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

[34]  Julian Togelius,et al.  Digging Deeper into Platform Game Level Design: Session Size and Sequential Features , 2012, EvoApplications.

[35]  Chek Tien Tan,et al.  Personalised gaming: a motivation and overview of literature , 2012, IE '12.

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

[37]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[38]  Georgios N. Yannakakis,et al.  Real-time challenge balance in an RTS game using rtNEAT , 2008, 2008 IEEE Symposium On Computational Intelligence and Games.