Exact Dynamic Programming for decentralized POMDPs with lossless policy compression

Abdeslam Boularias, Brahim Chaib-Draa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Scopus citations

Abstract

High dimensionality of belief space in DEC-POMDPs is one of the major causes that makes the optimal joint policy computation intractable. The belief state for a given agent is a probability distribution over the system states and the policies of other agents. Belief compression is an efficient POMDP approach that speeds up planning algorithms by projecting the belief state space to a low-dimensional one. In this paper, we introduce a new method for solving DEC-POMDP problems, based on the compression of the policy belief space. The reduced policy space contains sequences of actions and observations that are linearly independent. We tested our approach on two benchmark problems, and the preliminary results confirm that Dynamic Programming algorithm scales up better when the policy belief is compressed.

Original languageEnglish (US)
Title of host publicationICAPS 2008 - Proceedings of the 18th International Conference on Automated Planning and Scheduling
Pages20-27
Number of pages8
StatePublished - 2008
Externally publishedYes
Event18th International Conference on Automated Planning and Scheduling, ICAPS 2008 - Sydney, NSW, Australia
Duration: Sep 14 2008Sep 18 2008

Publication series

NameICAPS 2008 - Proceedings of the 18th International Conference on Automated Planning and Scheduling

Other

Other18th International Conference on Automated Planning and Scheduling, ICAPS 2008
Country/TerritoryAustralia
CitySydney, NSW
Period9/14/089/18/08

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Exact Dynamic Programming for decentralized POMDPs with lossless policy compression'. Together they form a unique fingerprint.

Cite this