Reference : Q-value functions for decentralized POMDPs
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Q-value functions for decentralized POMDPs
Oliehoek, Frans A. [> >]
Vlassis, Nikos mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Proc Int. Joint Conf. on Autonomous Agents and Multi-Agent Systems
Int. Joint Conf. on Autonomous Agents and Multi-Agent Systems
[en] Planning in single-agent models like MDPs and POMDPs can be carried out by resorting to Q-value functions: a (near-) optimal Q-value function is computed in a recursive manner by dynamic programming, and then a policy is extracted from this value function. In this paper we study whether similar Q-value functions can be defined in decentralized POMDP models (Dec-POMDPs), what the cost of computing such value functions is, and how policies can be extracted from such value functions. Using the framework of Bayesian games, we argue that searching for the optimal Q-value function may be as costly as exhaustive policy search. Then we analyze various approximate Q-value functions that allow efficient computation. Finally, we describe a family of algorithms for extracting policies from such Q-value functions.

File(s) associated to this reference

Fulltext file(s):

Open access
download.pdfPublisher postprint171.49 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.