@conference {1508621,
title = {Introducing Communication in Dis-POMDPs with Locality of Interaction },
booktitle = {IEEE International conference on Intelligent Agent Technology (IAT)},
year = {2008},
abstract = {While Distributed POMDPs have become popular for
modeling multiagent systems in uncertain domains, it is the
Networked Distributed POMDPs (ND-POMDPs) model {\textemdash}
a model tailored to real agent networks {\textemdash} that has begun
to scale-up the number of agents. However, prior work
in ND-POMDPs has failed to address communication, a
shortcoming that has the side-effect of limiting the planning
horizon. In particular, without communication, the size of
a local policy at each agent within the ND-POMDPs grows
exponentially in the time horizon. To overcome this problem, we extend existing algorithms (LID-JESP and SPIDER) so that agents periodically communicate their observation and action histories with each other. After communication, agents can start from new synchronized belief
states. While by introducing communication, we can avoid
the exponential growth in the size of local policies at agents,
the key idea is to avoid an exponential number of synchronized belief states after communication. To this end, we
introduce an idea that is similar the Point-based Value Iteration (PBVI) algorithm and approximate the value function with a fixed number of representative points and their
α vectors. Our experimental results show that we can obtain much longer policies than existing algorithms as long
as the interval between communications is small.},
author = {M. Tasaki and Y. Yabu and Y. Iwanari and M. Yokoo and M. Tambe and J. Marecki and P. Varakantham}
}