Quantifying Human Rationality in Ad-hoc Teamwork (2022)
Yair Hanina, Reuth Mirsky, William Macke, and Peter Stone
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''.
In AAMAS workshop on Autonomous Robots and Multirobot Systems (ARMS), Online, May 2022.

Peter Stone Faculty pstone [at] cs utexas edu