Super Mario as a String: Platformer Level Generation Via LSTMs

The procedural generation of video game levels has existed for at least 30 years, but only recently have machine learning approaches been used to generate levels without specifying the rules for generation. A number of these have looked at platformer levels as a sequence of characters and performed generation using Markov chains. In this paper we examine the use of Long Short-Term Memory recurrent neural networks (LSTMs) for the purpose of generating levels trained from a corpus of Super Mario Brothers levels. We analyze a number of different data representations and how the generated levels fit into the space of human authored Super Mario Brothers levels.

[1]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[2]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[3]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[4]  Michael Mateas,et al.  Sampling Hyrule: Multi-Technique Probabilistic Level Generation for Action Role Playing Games , 2015, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[5]  Marcus Rohrbach,et al.  Translating Videos to Natural Language Using Deep Recurrent Neural Networks , 2014, NAACL.

[6]  Michael Mateas,et al.  Tanagra: a mixed-initiative level design tool , 2010, FDG.

[7]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[8]  Santiago Ontañón,et al.  A Hierarchical MdMC Approach to 2D Video Game Map Generation , 2015, AIIDE.

[9]  Brian J. Taylor,et al.  Learning Causal Models of Relational Domains , 2010, AAAI.

[10]  Alessandro Canossa,et al.  Towards a Procedural Evaluation Technique: Metrics for Level Design , 2015, FDG.

[11]  Julian Togelius,et al.  Linear levels through n-grams , 2014, MindTrek.

[12]  Santiago Ontañón,et al.  Generating Maps Using Markov Chains , 2013, AIIDE 2013.

[13]  J. Koenderink.  Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[14]  Michael Mateas,et al.  MCMCTS PCG 4 SMB: Monte Carlo Tree Search to Guide Platformer Level Generation , 2021, Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.

[15]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[16]  Matthew Guzdial,et al.  Toward Game Level Generation from Gameplay Videos , 2016, ArXiv.

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

[18]  Santiago Ontañón,et al.  Experiments in map generation using Markov chains , 2014, FDG.

[19]  Olana Missura,et al.  Graph Grammars for Super Mario Bros Levels , 2015, FDG.

[20]  Corbeil-Essonnes.  The Legend of Zelda , 2011 .

[21]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[22]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[23]  Wojciech Zaremba,et al.  Learning to Execute , 2014, ArXiv.

[24]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[25]  Morteza Behrooz,et al.  The Learning of Zelda: Data-Driven Learning of Level Topology , 2015 .

[26]  Gillian Smith,et al.  Analyzing the expressive range of a level generator , 2010, PCGames@FDG.

[27]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Noor Shaker,et al.  Alone We Can Do So Little, Together We Can Do So Much: A Combinatorial Approach for Generating Game Content , 2014, AIIDE.

[29]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.