Super Mario as a String: Platformer Level Generation Via LSTMs
This addresses the challenge of automated level generation for platformer games, but it is incremental as it builds on existing sequence-based methods like Markov chains.
The paper tackled the problem of generating video game levels without manually specifying rules by using Long Short-Term Memory (LSTM) recurrent neural networks trained on Super Mario Brothers levels, analyzing different data representations and comparing generated levels to human-authored ones.
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.