RECURSIVE ALGORITHMS FOR OPTIMAL SOLUTIONS OF STOCHASTIC TEAMS WITH DECENTRALIZED INFORMATION.

Research output: Contribution to journalConference article

Abstract

The authors consider a class of stochastic team and nonzero-sum game problems with more than two agents who have access to decentralized information and may build their own subjective probability models to be used in the decision process. There is, in general, no compatibility between different models built by different agents, and this makes the available theory on teams and games inapplicable to this problem. The authors also discuss different equilibrium solutions to the team and game problems in this multimodeling framework, and develop convergent algorithms which would lead to such an equilibrium under a number of conditions and for different probabilistic models. As a byproduct of this analysis, a recursive algorithm is obtained which provides a solution to quadratic teams when the underlying distributions are not Gaussian.

Original languageEnglish (US)
Pages (from-to)231-236
Number of pages6
JournalProceedings of the American Control Conference
StatePublished - Dec 1 1985

Fingerprint

Byproducts
Statistical Models

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

RECURSIVE ALGORITHMS FOR OPTIMAL SOLUTIONS OF STOCHASTIC TEAMS WITH DECENTRALIZED INFORMATION. / Basar, M Tamer; Li, Shu.

In: Proceedings of the American Control Conference, 01.12.1985, p. 231-236.

Research output: Contribution to journalConference article

@article{af2cd69ceb4a4e5aa1ad01a9ff03649e,
title = "RECURSIVE ALGORITHMS FOR OPTIMAL SOLUTIONS OF STOCHASTIC TEAMS WITH DECENTRALIZED INFORMATION.",
abstract = "The authors consider a class of stochastic team and nonzero-sum game problems with more than two agents who have access to decentralized information and may build their own subjective probability models to be used in the decision process. There is, in general, no compatibility between different models built by different agents, and this makes the available theory on teams and games inapplicable to this problem. The authors also discuss different equilibrium solutions to the team and game problems in this multimodeling framework, and develop convergent algorithms which would lead to such an equilibrium under a number of conditions and for different probabilistic models. As a byproduct of this analysis, a recursive algorithm is obtained which provides a solution to quadratic teams when the underlying distributions are not Gaussian.",
author = "Basar, {M Tamer} and Shu Li",
year = "1985",
month = "12",
day = "1",
language = "English (US)",
pages = "231--236",
journal = "Proceedings of the American Control Conference",
issn = "0743-1619",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - RECURSIVE ALGORITHMS FOR OPTIMAL SOLUTIONS OF STOCHASTIC TEAMS WITH DECENTRALIZED INFORMATION.

AU - Basar, M Tamer

AU - Li, Shu

PY - 1985/12/1

Y1 - 1985/12/1

N2 - The authors consider a class of stochastic team and nonzero-sum game problems with more than two agents who have access to decentralized information and may build their own subjective probability models to be used in the decision process. There is, in general, no compatibility between different models built by different agents, and this makes the available theory on teams and games inapplicable to this problem. The authors also discuss different equilibrium solutions to the team and game problems in this multimodeling framework, and develop convergent algorithms which would lead to such an equilibrium under a number of conditions and for different probabilistic models. As a byproduct of this analysis, a recursive algorithm is obtained which provides a solution to quadratic teams when the underlying distributions are not Gaussian.

AB - The authors consider a class of stochastic team and nonzero-sum game problems with more than two agents who have access to decentralized information and may build their own subjective probability models to be used in the decision process. There is, in general, no compatibility between different models built by different agents, and this makes the available theory on teams and games inapplicable to this problem. The authors also discuss different equilibrium solutions to the team and game problems in this multimodeling framework, and develop convergent algorithms which would lead to such an equilibrium under a number of conditions and for different probabilistic models. As a byproduct of this analysis, a recursive algorithm is obtained which provides a solution to quadratic teams when the underlying distributions are not Gaussian.

UR - http://www.scopus.com/inward/record.url?scp=0022221427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022221427&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0022221427

SP - 231

EP - 236

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

SN - 0743-1619

ER -