Generating Lode Runner Levels by Learning Player Paths with LSTMs

TL;DR

This paper introduces a method that uses LSTM networks to learn player paths from gameplay videos and generate coherent Lode Runner levels, improving controllability and coherence over previous PCGML methods.

Contribution

The novel approach combines player path learning with level generation, enhancing the quality and coherence of generated levels in Lode Runner.

Findings

Generated levels are more coherent than existing PCGML methods.

LSTM effectively learns human-like player paths from video data.

Levels maintain gameplay plausibility and diversity.

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.