Gal A. Kaminka: Publications

Sorted by DateClassified by Publication TypeClassified by TopicGrouped by Student (current)Grouped by Former Students

Ad Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination

Peter Stone, Gal A. Kaminka, Sarit Kraus, and Jeffrey Rosenschein. Ad Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination. In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10) , 2010.

Download

[PDF]130.3kB  

Abstract

As autonomous agents proliferate in the real world, both in softwareand robotic settings, they will increasingly need to band together forcooperative activities with previously unknown or unfamiliarteammates. In such ad hoc team formation settings, teamstrategies cannot be developed a priori. Rather, an agent must beprepared to cooperate with many types of teammates: it mustcollaborate without pre-coordination. This paper challenges the AIcommunity to develop theory and implemented prototypes of ad hoc teamagents. It defines the concept of ad hoc team agents, specifies anevaluation paradigm, and provides examples of possible theoretical andempirical approaches to addressing the challenge. The goal is toencourage progress towards this ambitious, newly realistic, andincreasingly important research goal.

Additional Information

BibTeX

@InProceedings{aaai10,
author = {Peter Stone and Gal A. Kaminka and Sarit Kraus and Jeffrey Rosenschein},
title = {Ad Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination},
booktitle = AAAI-10,
OPTcrossref = {},
OPTkey = {},
OPTpages = {},
year = {2010},
OPTeditor = {},
OPTvolume = {},
OPTnumber = {},
OPTseries = {},
OPTaddress = {},
OPTmonth = {},
OPTorganization = {},
OPTpublisher = {},
OPTnote = {},
OPTannote = {},
OPTurl = {},
OPTdoi = {},
OPTissn = {},
OPTlocalfile = {},
abstract = {As autonomous agents proliferate in the real world, both in software
and robotic settings, they will increasingly need to band together for
cooperative activities with previously unknown or unfamiliar
teammates. In such \emph{ad hoc team} formation settings, team
strategies cannot be developed a priori.  Rather, an agent must be
prepared to cooperate with many types of teammates: it must
collaborate without pre-coordination.  This paper challenges the AI
community to develop theory and implemented prototypes of ad hoc team
agents.  It defines the concept of ad hoc team agents, specifies an
evaluation paradigm, and provides examples of possible theoretical and
empirical approaches to addressing the challenge.  The goal is to
encourage progress towards this ambitious, newly realistic, and
increasingly important research goal.},
  wwwnote = {},
}

Generated by bib2html.pl (written by Patrick Riley ) on Mon Nov 16, 2020 22:25:46