Please use this identifier to cite or link to this item:
Title: PCGRL : procedural content generation via reinforcement learning
Authors: Khalifa, Ahmed
Bontrager, Philip
Earle, Sam
Togelius, Julian
Keywords: Computer games -- Design
Level design (Computer science)
Machine learning
Artificial intelligence
Issue Date: 2020
Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Citation: Khalifa, A., Bontrager, P., Earle, S., & Julian, T. (2020). PCGRL : procedural content generation via reinforcement learning. Proceedings of the Sixteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-20), 16(1), 95-101.
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.
ISBN: 9781577358497
Appears in Collections:Scholarly Works - InsDG

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.16 MBAdobe PDFView/Open Request a copy

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.