Search-based procedural content generation for GVG-LG

Abstract Search-based Procedural Content Generation has been proven an efficient technique for the generation of different and diverse types of content. In this article, we generate general levels for 2D games using the FI2POP genetic algorithm. Generating entertaining levels is subjective. Therefore in this work, we focus on the aesthetics and difficulty of a level. For experimentation purposes, we generated levels for five different games in the General Video Game Level Generation track. Our results indicate that the generated levels are symmetrical, balanced, dense and reachable.

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

[2]  Julian Togelius,et al.  Procedural Content Generation via Machine Learning (PCGML) , 2017, IEEE Transactions on Games.

[3]  David Oranchak.  Evolutionary Algorithm for Generation of Entertaining Shinro Logic Puzzles , 2010, EvoApplications.

[4]  Julian Togelius,et al.  Procedural Content Generation in Games , 2016, Computational Synthesis and Creative Systems.

[5]  Julian Togelius,et al.  General Video Game Level Generation , 2016, GECCO.

[6]  Carlos Cotta,et al.  Evolution of Artificial Terrains for Video Games Based on Accessibility , 2010, EvoApplications.

[7]  Julian Togelius,et al.  An experiment in automatic game design , 2008, 2008 IEEE Symposium On Computational Intelligence and Games.

[8]  Philippe Pasquier,et al.  Towards a Generic Framework for Automated Video Game Level Creation , 2010, EvoApplications.

[9]  Julian Togelius,et al.  Search-Based Procedural Content Generation , 2010, EvoApplications.

[10]  Julian Togelius,et al.  The 2010 Mario AI Championship: Level Generation Track , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[11]  Daniel A. Ashlock,et al.  Automatic generation of game elements via evolution , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

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

[13]  Santiago Ontañón,et al.  Understanding mario: an evaluation of design metrics for platformers , 2017, FDG.

[14]  Julian Togelius,et al.  Evolving levels for Super Mario Bros using grammatical evolution , 2012, 2012 IEEE Conference on Computational Intelligence and Games (CIG).

[15]  Tom Schaul,et al.  A video game description language for model-based or interactive learning , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).