Networked Distributed POMDPs: DCOP-Inspired Distributed
POMDPs
Ranjit Nair, Pradeep Varakantham, Milind Tambe, and
Makoto Yokoo
Abstract
In many real-world multiagent applications such as
distrib-
uted sensor nets, a network of agents is formed based on each agent s
limited
interactions with a small number of neighbors. While distributed POMDPs
capture
the real-world uncertainty in multiagent domains, they fail to exploit
such
locality of interaction. Distributed constraint opti- mization (DCOP)
captures
the locality of interaction but fails to capture planning under
uncertainty.
This paper present a new model synthesized from distributed POMDPs and
DCOPs,
called Networked Distributed POMDPs (ND-POMDPs). Exploiting network
structure
enables us to present two novel algorithms for ND-POMDPs: a distributed
policy
gen- eration algorithm that performs local search and a systematic
policy
search that is guaranteed to reach the global optimal.