PCGRL: Procedural Content Generation via Reinforcement Learning

Ahmed Khalifa, Philip Bontrager, Sam Earle, Julian Togelius
1/24/2020
cs.LGcs.AIstat.ML

Official code: amidos2006/gym-pcgrl (134 stars, MIT, last commit 2024-12-13).

Abstract

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcement learning to learn how to take the next action so that the expected final level quality is maximized. This approach can be used when few or no examples exist to train from, and the trained generator is very fast. We investigate three different ways of transforming two-dimensional level design problems into Markov decision processes and apply these to three game environments.

View on arXivView PDF

Code Implementations(1)

amidos2006/gym-pcgrlOfficial100%
MIT

A package for "Procedural Content Generation via Reinforcement Learning" OpenAI Gym interface.

13432Python, DockerfileOct 28, 20191 years agoMIT

Similar Papers

Video Game Level Design as a Multi-Agent Reinforcement Learning Problem

91% match2025

Story Shaping: Teaching Agents Human-like Behavior with Stories

86% match2023

Learning Curricula in Open-Ended Worlds

86% match1 repo1412023

Augmenting Game AI with Deep Reinforcement Learning

85% match2026

PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning

85% match1 repo32025

ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generation

85% match1 repo32024

Cite this paper

@article{khalifa2020pcgrl,
  title  = {PCGRL: Procedural Content Generation via Reinforcement Learning},
  author = {Ahmed Khalifa and Philip Bontrager and Sam Earle and Julian Togelius},
  year   = {2020},
  eprint = {2001.09212},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2001.09212}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2001.09212.svg)](https://codeofpaper.com/paper/2001.09212)

Discussion