Aaron Isaksen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Aaron Isaksen has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Andy Nealen
Tandon School of Engineering New York University New York NY USA
3 shared publications - Julian Togelius
New York University, New York, USA
3 shared publications - Adam Summerville
Department of Computational Media University of California 95064 Santa Cruz CA USA
2 shared publications - Amy K. Hoover
College of Arts, Media and Design Northeastern University 02115 Boston MA USA
2 shared publications - Christoffer Holmgård
Duck and Cover Games ApS 1311 Copenhagen K Denmark
2 shared publications - Matthew Guzdial
School of Interactive Computing Georgia Institute of Technology
2 shared publications
Latest Publications
- Top Cited Papers
- 12 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (3) , 257-270
Procedural Content Generation via Machine Learning (PCGML)
This survey explores Procedural Content Generation via Machine Learning (PCGML), the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, LSTM networks, autoencoders, and deep convolutional networks; Markov models, n-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.
- 12 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (3) , 257-270
Top Cited PapersProcedural Content Generation via Machine Learning (PCGML)
This survey explores Procedural Content Generation via Machine Learning (PCGML), the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, LSTM networks, autoencoders, and deep convolutional networks; Markov models, n-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.
- Open Access
Procedural Content Generation via Machine Learning (PCGML)
This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, long short-term memory (LSTM) networks, autoencoders, and deep convolutional networks; Markov models, $n$-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.
Open AccessProcedural Content Generation via Machine Learning (PCGML)
This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the resulting generated content. Multiple PCGML methods are covered, including neural networks, long short-term memory (LSTM) networks, autoencoders, and deep convolutional networks; Markov models, $n$-grams, and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in the application of PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.
- 8 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (2) , 182-194
Exploring Game Space of Minimal Action Games via Parameter Tuning and Survival Analysis
Game designers can use computer-aided game design methods to model how players may experience the perceived difficulty of a game. We present methods to generate and analyze the difficulty of a wide variety of minimal action game variants throughout game space, where each point in this abstract design space represents a unique game variant. Focusing on a parameterized version of Flappy Bird, we predict hazard rates and difficulty curves using automatic play testing, Monte-Carlo simulation, a player model based on human motor skills (precision and actions per second), and survival analysis of score histograms. We demonstrate our techniques using simulated game play and actual game data from over 106 million play sessions of a popular online Flappy Bird variant, showing quantitative reasons why balancing a game for a wide range of player skill can be difficult. Some applications of our techniques include searching for a specific difficulty, game space visualization, computational creativity to find unique variants, and tuning game balance to adjust the difficulty curve even when game parameters are time-varying, score-dependent, or changing based on game progress.
- 8 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (2) , 182-194
Exploring Game Space of Minimal Action Games via Parameter Tuning and Survival Analysis
Game designers can use computer-aided game design methods to model how players may experience the perceived difficulty of a game. We present methods to generate and analyze the difficulty of a wide variety of minimal action game variants throughout game space, where each point in this abstract design space represents a unique game variant. Focusing on a parameterized version of Flappy Bird, we predict hazard rates and difficulty curves using automatic play testing, Monte-Carlo simulation, a player model based on human motor skills (precision and actions per second), and survival analysis of score histograms. We demonstrate our techniques using simulated game play and actual game data from over 106 million play sessions of a popular online Flappy Bird variant, showing quantitative reasons why balancing a game for a wide range of player skill can be difficult. Some applications of our techniques include searching for a specific difficulty, game space visualization, computational creativity to find unique variants, and tuning game balance to adjust the difficulty curve even when game parameters are time-varying, score-dependent, or changing based on game progress.