Research on ad hoc teamwork has been around for at least 20 years, but it was first introduced as a formal challenge by Stone et al. in 2010. The challenge discussed in that paper is:
To create an autonomous agent that is able to efficiently and robustly collaborate with previously unknown teammates on tasks to which they are all individually capable of contributing as team members.
Since 2010, hundreds of papers that explicitly state ``ad hoc team'' or ``ad hoc teamwork'' have been published - 632 according to Google Scholar during the writing of this call - and much more address tightly connected challenges such as ``zero-shot'' or ``cold start'' teamwork. Moreover, much of the prevalent work on personalizing interactions with new human teammates can be viewed as ad-hoc teamwork.
The aim of this workshop is to build a united, supportive research community for ad hoc teamwork and related problems. It will facilitate discussions between different research labs in academia and industry, identify the main attributes that can vary between ad hoc teamwork tasks, and discuss the progress that has been made in this field so far, while identifying the next immediate open problems the community should address.
University of Central Florida
Sony AI
Heriot-Watt University,
United Kingdom
ignacio.carlucho@hw.ac.uk
University of Birmingham
United Kingdom
University of Edinburgh,
United Kingdom
University of Texas at Austin,
United States
Bar Ilan University,
Ramat Gan, Israel
University of Edinburgh,
United Kingdom
University of Texas at Austin,
USA
University of Birmingham,
United Kingdom