Generating Lode Runner Levels by Learning Player Paths with LSTMs
arXiv:2107.12532 · doi:10.1145/3472538.3472602
Abstract
Machine learning has been a popular tool in many different fields, including procedural content generation. However, procedural content generation via machine learning (PCGML) approaches can struggle with controllability and coherence. In this paper, we attempt to address these problems by learning to generate human-like paths, and then generating levels based on these paths. We extract player path data from gameplay video, train an LSTM to generate new paths based on this data, and then generate game levels based on this path data. We demonstrate that our approach leads to more coherent levels for the game Lode Runner in comparison to an existing PCGML approach.
arXiv comment7 pages, 6 figures, Workshop on Procedural Content Generation
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Super Mario as a String: Platformer Level Generation Via LSTMs
- The VGLC: The Video Game Level Corpus
- Toward Game Level Generation from Gameplay Videos
- Controllable Level Blending between Games using Variational Autoencoders
- Exploring Level Blending across Platformers via Paths and Affordances
- A Unified Neural Coherence Model