Influence-optimistic local values for multiagent planning

Conference paper (2015)

Authors

F.A. Oliehoek Universiteit van Amsterdam
M.T.J. Spaan Algorithmics - EEMCS
Stefan Witwicki Swiss Federal Institute of Technology
Research Group
Algorithmics (EEMCS) (TU Delft)
Multi-agent planning Factored Dec-POMDPs
More Info
expand_more

Published Date

01-01-2015

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Software Technology

Research Group

Algorithmics

Abstract

Over the last decade, methods for multiagent planning under uncertainty have increased in scalability. However, many methods assume value factorization or are not able to provide quality guarantees. We propose a novel family of influence-optimistic upper bounds on the optimal value for problems with lOOs of agents that do not exhibit value fec-torization.