@COMMENT This file was generated by bib2html.pl <https://sourceforge.net/projects/bib2html/> version 0.94
@COMMENT written by Patrick Riley <http://sourceforge.net/users/patstg/>
@COMMENT This file came from Gal A. Kaminka's publication pages at
@COMMENT http://www.cs.biu.ac.il/~galk/publications/
@InProceedings{icra10dan,
author = {Gal A. Kaminka and Dan Erusalimchik and Sarit Kraus},
title = {Adaptive Multi-Robot Coordination: A Game-Theoretic Perspective},
booktitle = ICRA-10,
OPTcrossref = {},
OPTkey = {},
OPTpages = {},
year = {2010},
OPTeditor = {},
OPTvolume = {},
OPTnumber = {},
OPTseries = {},
OPTaddress = {},
OPTmonth = {},
OPTorganization = {},
OPTpublisher = {},
OPTnote = {},
OPTannote = {},
OPTurl = {},
OPTdoi = {},
OPTissn = {},
OPTlocalfile = {},
abstract = {Multi-robot systems researchers have been investigating adaptive coordination methods for
improving spatial coordination in teams. Such methods adapt the coordination method to the dynamic
changes in  density of the robots. Unfortunately, while their empirical success is evident, none of
these methods has been  understood in the context of existing formal work on multi-robot learning. This
paper presents a  reinforcement-learning approach to coordination algorithm selection, which
is not only shown to work well in experiments, but is also analytically grounded. We present a
reward  function (\emph{Effectiveness Index}, EI), that reduces time and resources spent coordinating,
and maximizes the time between conflicts that require coordination. It does this by measuring
\emph{the resource spending velocity}.  We empirically show its success in several domains, including
robots in virtual worlds, simulated robots, and physical AIBO robots executing foraging. In addition,
we analytically explore the reasons that EI works well.  We show that under some assumptions, spatial
coordination opportunities can be modeled as matrix games in which the payoffs to the robots are unknown,
but are directly a function of EI estimates. The use of  reinforcement learning leads to robots maximizing
their EI rewards in equilibrium. This work is a step towards  bridging the gap between the theoretical
study of interactions, and their use in multi-robot coordination. },
  wwwnote = {A slightly different version of this paper also appears in Proceedings of the Adaptive Agents Workshop of the AAMAS 2009 Conference.},
}