Latent Space Alignment Using Adversarially Guided Self-Play
Name
Latent Space Alignment Using Adversarially Guided Self-Play.pdf
Description
Published version
Size
2.89 MB
Format
Adobe PDF
Checksum (MD5)
0457a19ac01b1a26699eaee279f72c93
Author(s)
Tucker, Mycal
Zhou, Yilun
Shah, Julie A
Date Issued
August 26, 2022
Journal
International Journal of Human–Computer Interaction
Publisher
Taylor & Francis
Citation
Tucker, M., Zhou, Y., & Shah, J. A. (2022). Latent Space Alignment Using Adversarially Guided Self-Play. International Journal of Human–Computer Interaction, 38(18–20), 1753–1771.
Version
Final published version
Abstract
We envision a world in which robots serve as capable partners in heterogeneous teams composed of other robots or humans. A crucial step towards such a world is enabling robots to learn to use the same representations as their partners; with a shared representation scheme, information may be passed among teammates. We define the problem of learning a fixed partner’s representation scheme as that of latent space alignment and propose metrics for evaluating the quality of alignment. While techniques from prior art in other fields may be applied to the latent space alignment problem, they often require interaction with partners during training time or large amounts of training data. We developed a technique, Adversarially Guided Self-Play (ASP), that trains agents to solve the latent space alignment problem with little training data and no access to their pre-trained partners. Simulation results confirmed that, despite using less training data, agents trained by ASP aligned better with other agents than agents trained by other techniques. Subsequent human-participant studies involving hundreds of Amazon Mechanical Turk workers showed how laypeople understood our machines enough to perform well on team tasks and anticipate their machine partner’s successes or failures.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivatives
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1080/10447318.2022.2083463
