mlsanityData to 7 Oct 2026

Super Mario as a String: Platformer Level Generation Via LSTMs

arXiv 1603.00930 ↗First posted 2 Mar 2016cs.NE cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 6; 2024: 9; 2025: 6; 2026: 3.

40 papers.

Sort:

By area:

  1. 2024Large Language Models and Games: A Survey and Roadmapcited by 91
  2. 2023Level Generation Through Large Language Modelscited by 68
  3. 2023MarioGPT: Open-Ended Text2Level Generation through Large Language Modelscited by 63
  4. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  5. 2021On the Importance of Environments in Human-Robot Coordinationcited by 37
  6. 2021Generating and Blending Game Levels via Quality-Diversity in the Latent Space of a Variational Autoencodercited by 27
  7. 2024Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integrationcited by 22
  8. 2024Word2World: Generating Stories and Worlds through Large Language Modelscited by 18
  9. 2022Path of Destruction: Learning an Iterative Level Generator Using a Small Datasetcited by 14
  10. 2024Unbounded: A Generative Infinite Game of Character Life Simulationcited by 14
  11. 2026MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Enginescited by 12
  12. 2021TaikoNation: Patterning-focused Chart Generation for Rhythm Action Gamescited by 9
28 more
  1. 2021Tile Embedding: A General Representation for Procedural Level Generation via Machine Learningcited by 9
  2. 2022Open-Ended Evolution for Minecraft Building Generationcited by 9
  3. 2024Missed Connections: Lateral Thinking Puzzles for Large Language Modelscited by 9
  4. 2024PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generatorscited by 7
  5. 2025AnimeGamer: Infinite Anime Life Simulation with Next Game State Predictioncited by 7
  6. 2022Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometrycited by 5
  7. 2024Measuring Diversity of Game Scenarioscited by 5
  8. 2023Evolving Flying Machines in Minecraft Using Quality Diversitycited by 4
  9. 2021Adversarial Random Forest Classifier for Automated Game Designcited by 3
  10. 2021Generating Lode Runner Levels by Learning Player Paths with LSTMscited by 3
  11. 2025Word2Minecraft: Generating 3D Game Levels through Large Language Modelscited by 3
  12. 2022Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizescited by 2
  13. 2023Procedural Content Generation via Knowledge Transformation (PCG-KT)cited by 2
  14. 2024Guided Game Level Repair via Explainable AIcited by 2
  15. 2021Pairing Character Classes in a Deathmatch Shooter Game via a Deep-Learning Surrogate Modelcited by 1
  16. 2021Ensemble Learning For Mega Man Level Generationcited by 1
  17. 2022Clustering-based Tile Embedding (CTE): A General Representation for Level Design with Skewed Tile Distributionscited by 1
  18. 2023Reconstructing Existing Levels through Level Inpaintingcited by 1
  19. 2025Analysis of Robustness of a Large Game Corpuscited by 1
  20. 2025Level Generation with Constrained Expressive Rangecited by 1
  21. 2025Video Game Level Design as a Multi-Agent Reinforcement Learning Problemcited by 1
  22. 2021Level generation and style enhancement -- deep learning for game development overviewcited by 0
  23. 2022Latent Combinational Game Designcited by 0
  24. 2023Evolutionary Machine Learning and Gamescited by 0
  25. 2024Speedrunning and path integralscited by 0
  26. 2025Text-to-Level Diffusion Models With Various Text Encoders for Super Mario Broscited by 0
  27. 2026Learning Local Constraints for Reinforcement-Learned Content Generatorscited by 0
  28. 2026Representing and Generating Levels Over Time through Playtrace Reconstructive Partitioningcited by 0