• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Quantifying Human Rationality in Ad-hoc Teamwork.
Yair Hanina, Reuth
Mirsky, William Macke, and Peter
Stone.
In AAMAS workshop on Autonomous Robots and Multirobot Systems (ARMS), May 2022.
Ad-hoc teamwork is defined as the task of collaborating with teammates without pre-coordination. When the ad hoc agent is a robot that needs to collaborate with people, it cannot assume that its teammates will behave optimally or legibly. By providing a means to learn human policies in ad-hoc teamwork, this work will help create robots that can adapt to a new human agent and work together to achieve a common goal. We focus on a simple, yet powerful model for representing agents using the concept of bounded rationality. Our preliminary results exemplify how such a model can be used in a domain from the ad-hoc teamwork literature called ``the tool fetching domain''.
@InProceedings{ARMS22-REUTH,
author = {Yair Hanina and Reuth Mirsky and William Macke and Peter Stone},
title = {Quantifying Human Rationality in Ad-hoc Teamwork},
booktitle = {AAMAS workshop on Autonomous Robots and Multirobot Systems (ARMS)},
location = {Online},
month = {May},
year = {2022},
abstract = {
Ad-hoc teamwork is defined as the task of collaborating with teammates
without pre-coordination. When the ad hoc agent is a robot that needs
to collaborate with people, it cannot assume that its teammates will
behave optimally or legibly. By providing a means to learn human policies
in ad-hoc teamwork, this work will help create robots that can adapt to a
new human agent and work together to achieve a common goal.
We focus on a simple, yet powerful model for representing agents using the
concept of bounded rationality. Our preliminary results exemplify how such
a model can be used in a domain from the ad-hoc teamwork literature called
``the tool fetching domain''.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Sat Nov 15, 2025 21:30:20