Procedural Content Generation using Behavior Trees (PCGBT)

TL;DR

This paper introduces PCGBT, a novel approach that uses behavior trees to model and generate game content, enabling modular and dynamic level creation for classic platformers and dungeon layouts.

Contribution

The paper presents a new paradigm of using behavior trees for procedural content generation, allowing modular and dynamic content creation in games.

Findings

Successfully modeled level generators for Super Mario Bros., Mega Man, and Metroid.

Demonstrated modularity and flexibility in content generation.

Discussed potential extensions and applications of PCGBT.

Abstract

Behavior trees (BTs) are a popular method for modeling NPC and enemy AI behavior and have been widely used in commercial games. In this work, rather than use BTs to model game playing agents, we use them for modeling game design agents, defining behaviors as content generation tasks rather than in-game actions. Similar to how traditional BTs enable modeling behaviors in a modular and dynamic manner, BTs for PCG enable simple subtrees for generating parts of levels to be combined modularly to form complex trees for generating whole levels as well as generators that can dynamically vary the generated content. We refer to this approach as Procedural Content Generation using Behavior Trees, or PCGBT, and demonstrate it by using BTs to model generators for Super Mario Bros., Mega Man and Metroid levels as well as dungeon layouts and discuss several ways in which this paradigm could be applied and extended in the future.