Please use this identifier to cite or link to this item:
Title: Learning controllable content generators
Authors: Earle, Sam
Edwards, Maria
Khalifa, Ahmed
Bontrager, Philip
Togelius, Julian
Keywords: Computer games -- Design
Level design (Computer science)
Machine learning
Artificial intelligence
Reinforcement learning
Issue Date: 2021
Publisher: Institute of Electrical and Electronics Engineers
Citation: Earle, S., Edwards, M., Khalifa, A., Bontrager, P., & Togelius, J. (2021). Learning controllable content generators. 3rd IEEE Conference on Games.
Abstract: It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user specified heuristic. To ensure that these generators’ output is sufficiently diverse (that is, not amounting to the reproduction of a single optimal level configuration), the generation process is constrained such that the initial seed results in some variance in the generator’s output. However, this results in a loss of control over the generated content for the human user. We propose to train generators capable of producing controllably diverse output, by making them “goal-aware.” To this end, we add conditional inputs representing how close a generator is to some heuristic, and also modify the reward mechanism to incorporate that value. Testing on multiple domains, we show that the resulting level generators are capable of exploring the space of possible levels in a targeted, controllable manner, producing levels of comparable quality as their goal-unaware counterparts, that are diverse along designer-specified dimensions.
Appears in Collections:Scholarly Works - InsDG

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

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