Decentralized control of partially observable Markov decision processes

Christopher Amato, Girish Chowdhary, Alborz Geramifard, N. Kemal Üre, Mykel J. Kochenderfer

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


Markov decision processes (MDPs) are often used to model sequential decision problems involving uncertainty under the assumption of centralized control. However, many large, distributed systems do not permit centralized control due to communication limitations (such as cost, latency or corruption). This paper surveys recent work on decentralized control of MDPs in which control of each agent depends on a partial view of the world.We focus on a general framework where there may be uncertainty about the state of the environment, represented as a decentralized partially observable MDP (Dec-POMDP), but consider a number of subclasses with different assumptions about uncertainty and agent independence. In these models, a shared objective function is used, but plans of action must be based on a partial view of the environment. We describe the frameworks, along with the complexity of optimal control and important properties. We also provide an overview of exact and approximate solution methods as well as relevant applications. This survey provides an introduction to what has become an active area of research on these models and their solutions.

Original languageEnglish (US)
Title of host publication2013 IEEE 52nd Annual Conference on Decision and Control, CDC 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages8
ISBN (Print)9781467357173
StatePublished - Jan 1 2013
Externally publishedYes
Event52nd IEEE Conference on Decision and Control, CDC 2013 - Florence, Italy
Duration: Dec 10 2013Dec 13 2013

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0191-2216


Other52nd IEEE Conference on Decision and Control, CDC 2013

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization


Dive into the research topics of 'Decentralized control of partially observable Markov decision processes'. Together they form a unique fingerprint.

Cite this