DISTRIBUTED ALGORITHM FOR THE COMPUTATION OF NASH EQUILIBRIA IN LINEAR STOCHASTIC DIFFERENTIAL GAMES.

Research output: Contribution to conferencePaper

Abstract

In this paper, we study a class of two-person stochastic linear-quadratic differential games under multiple probabilistic modeling, and with each player acquiring a noisy measurement of the initial state. We obtain conditions for the existence and uniqueness of Nash equilibrium, and provide a method for iterative distributed computation of the solution. The distributed algorithm involves learning in the policy space, and it does not require that the players know each other's perception of the probabilistic model underlying the decision process. Such an iteration converges whenever the length of the time horizon is sufficiently small, and the limit is an affine policy for both players if the underlying distributions are jointly Gaussian.

Original languageEnglish (US)
Pages652-656
Number of pages5
StatePublished - Dec 1 1986

Fingerprint

Parallel algorithms
Statistical Models

ASJC Scopus subject areas

  • Engineering(all)

Cite this

DISTRIBUTED ALGORITHM FOR THE COMPUTATION OF NASH EQUILIBRIA IN LINEAR STOCHASTIC DIFFERENTIAL GAMES. / Li, Shu; Basar, M Tamer.

1986. 652-656.

Research output: Contribution to conferencePaper

@conference{fc700a76936b4fca9705e9397239d6a9,
title = "DISTRIBUTED ALGORITHM FOR THE COMPUTATION OF NASH EQUILIBRIA IN LINEAR STOCHASTIC DIFFERENTIAL GAMES.",
abstract = "In this paper, we study a class of two-person stochastic linear-quadratic differential games under multiple probabilistic modeling, and with each player acquiring a noisy measurement of the initial state. We obtain conditions for the existence and uniqueness of Nash equilibrium, and provide a method for iterative distributed computation of the solution. The distributed algorithm involves learning in the policy space, and it does not require that the players know each other's perception of the probabilistic model underlying the decision process. Such an iteration converges whenever the length of the time horizon is sufficiently small, and the limit is an affine policy for both players if the underlying distributions are jointly Gaussian.",
author = "Shu Li and Basar, {M Tamer}",
year = "1986",
month = "12",
day = "1",
language = "English (US)",
pages = "652--656",

}

TY - CONF

T1 - DISTRIBUTED ALGORITHM FOR THE COMPUTATION OF NASH EQUILIBRIA IN LINEAR STOCHASTIC DIFFERENTIAL GAMES.

AU - Li, Shu

AU - Basar, M Tamer

PY - 1986/12/1

Y1 - 1986/12/1

N2 - In this paper, we study a class of two-person stochastic linear-quadratic differential games under multiple probabilistic modeling, and with each player acquiring a noisy measurement of the initial state. We obtain conditions for the existence and uniqueness of Nash equilibrium, and provide a method for iterative distributed computation of the solution. The distributed algorithm involves learning in the policy space, and it does not require that the players know each other's perception of the probabilistic model underlying the decision process. Such an iteration converges whenever the length of the time horizon is sufficiently small, and the limit is an affine policy for both players if the underlying distributions are jointly Gaussian.

AB - In this paper, we study a class of two-person stochastic linear-quadratic differential games under multiple probabilistic modeling, and with each player acquiring a noisy measurement of the initial state. We obtain conditions for the existence and uniqueness of Nash equilibrium, and provide a method for iterative distributed computation of the solution. The distributed algorithm involves learning in the policy space, and it does not require that the players know each other's perception of the probabilistic model underlying the decision process. Such an iteration converges whenever the length of the time horizon is sufficiently small, and the limit is an affine policy for both players if the underlying distributions are jointly Gaussian.

UR - http://www.scopus.com/inward/record.url?scp=0022941104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022941104&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0022941104

SP - 652

EP - 656

ER -