Preliminary Poetics of Procedural Generation in Games

Karth Isaac
2018 DiGRA '18 - Proceedings of the 2018 DiGRA International Conference: The Game is the Message

Procedural Content Generation (PCG) is deeply embedded in many games. While there are many taxonomies of the applications of PCG, less attention has been given to the poetics of PCG. In this paper we present a poetics for generative systems, including a descriptive framework that introduces terms for complex systems (Apollonian order and Dionysian chaos), the form that describes the shape of the generated output (formal gestalt, individual, and repetition), the locus of the generative process (structure, surface, or locus gestalt), the kind of variation the generator uses (style, multiplicity, and cohesion) and the relationship between coherence and the content used as input for the generator. Rather than being mutually exclusive categories, generators can be considered to exhibit aspects of all of these at once.


Super Mario as a String: Platformer Level Generation Via LSTMs

Summerville Adam J. Mateas Michael
2016 DiGRA/FDG '16 - Proceedings of the First International Joint Conference of DiGRA and FDG

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 Bros. levels. We analyze a number of different data representations and how the generated levels fit into the space of human authored Super Mario Bros. levels.