Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/82049
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. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/82049 |
Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Learning_controllable_content_generators_2021.pdf Restricted Access | 1.89 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.