Interface design optimization as a multi-armed bandit problem

Lomas, J.D.; Forlizzi, Jodi; Poonwala, Nikhil; Patel, Nirmal; Shodhan, Sharan; Patel, Kishan; Koedinger, Kenneth R.; Brunskill, Emma

Interface design optimization as a multi-armed bandit problem

Conference paper (2016)

Authors

J.D. Lomas UC San Diego's Design Lab, University of California

Jodi Forlizzi Carnegie Mellon University

Nikhil Poonwala Carnegie Mellon University

Nirmal Patel Carnegie Mellon University

Sharan Shodhan Carnegie Mellon University

Kishan Patel Carnegie Mellon University

Kenneth R. Koedinger Carnegie Mellon University

Emma Brunskill Carnegie Mellon University

Affiliation

External organisation

Optimization Data-driven design Continuous improvement Educational games Multiarmed bandits

To reference this document use:

http://resolver.tudelft.nl/uuid:bb2d5cf4-226b-4df5-8535-e7082e2c5983

More Info

expand_more

Published Date

2016

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Affiliation

External organisation

Abstract

"Multi-armed bandits" offer a new paradigm for the AIassisted design of user interfaces. To help designers understand the potential, we present the results of two experimental comparisons between bandit algorithms and random assignment. Our studies are intended to show designers how bandits algorithms are able to rapidly explore an experimental design space and automatically select the optimal design configuration. Our present focus is on the optimization of a game design space. The results of our experiments show that bandits can make data-driven design more efficient and accessible to interface designers, but that human participation is essential to ensure that AI systems optimize for the right metric. Based on our results, we introduce several design lessons that help keep human design judgment in the loop. We also consider the future of human-technology teamwork in AI-assisted design and scientific inquiry. Finally, as bandits deploy fewer lowperforming conditions than typical experiments, we discuss ethical implications for bandits in large-scale experiments in education.