Dynamic robust games in MIMO systems

Research output: Contribution to journalArticle

Abstract

In this paper, we study dynamic robust power-allocation games in multiple-input-multiple-output systems under the imperfectness of the channel-state information at the transmitters. Using a robust pseudopotential-game approach, we show the existence of robust solutions in both discrete and continuous action spaces under suitable conditions. Considering the imperfectness in terms of the payoff measurement at the transmitters, we propose a COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (CODIPAS-RL) in which each transmitter learns its payoff function, as well as the associated optimal covariance matrix strategies. Under the heterogeneous CODIPAS-RL, the transmitters can use different learning patterns (heterogeneous learning) and different learning rates. We provide sufficient conditions for the almost-sure convergence of the heterogeneous learning to ordinary differential equations. Extensions of the CODIPAS-RL to It's stochastic differential equations are discussed.

Original languageEnglish (US)
Article number5699932
Pages (from-to)990-1002
Number of pages13
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume41
Issue number4
DOIs
StatePublished - Aug 1 2011

Fingerprint

MIMO systems
Transmitters
Reinforcement learning
Channel state information
Covariance matrix
Ordinary differential equations
Differential equations

Keywords

  • Dynamic games
  • learning
  • multiple-input-multiple-output (MIMO)
  • robust games

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Dynamic robust games in MIMO systems. / Hamidou, Tembine.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 41, No. 4, 5699932, 01.08.2011, p. 990-1002.

Research output: Contribution to journalArticle

@article{7e1c50a4f4ed4b809c72d852354d6486,
title = "Dynamic robust games in MIMO systems",
abstract = "In this paper, we study dynamic robust power-allocation games in multiple-input-multiple-output systems under the imperfectness of the channel-state information at the transmitters. Using a robust pseudopotential-game approach, we show the existence of robust solutions in both discrete and continuous action spaces under suitable conditions. Considering the imperfectness in terms of the payoff measurement at the transmitters, we propose a COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (CODIPAS-RL) in which each transmitter learns its payoff function, as well as the associated optimal covariance matrix strategies. Under the heterogeneous CODIPAS-RL, the transmitters can use different learning patterns (heterogeneous learning) and different learning rates. We provide sufficient conditions for the almost-sure convergence of the heterogeneous learning to ordinary differential equations. Extensions of the CODIPAS-RL to It's stochastic differential equations are discussed.",
keywords = "Dynamic games, learning, multiple-input-multiple-output (MIMO), robust games",
author = "Tembine Hamidou",
year = "2011",
month = "8",
day = "1",
doi = "10.1109/TSMCB.2010.2102751",
language = "English (US)",
volume = "41",
pages = "990--1002",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Dynamic robust games in MIMO systems

AU - Hamidou, Tembine

PY - 2011/8/1

Y1 - 2011/8/1

N2 - In this paper, we study dynamic robust power-allocation games in multiple-input-multiple-output systems under the imperfectness of the channel-state information at the transmitters. Using a robust pseudopotential-game approach, we show the existence of robust solutions in both discrete and continuous action spaces under suitable conditions. Considering the imperfectness in terms of the payoff measurement at the transmitters, we propose a COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (CODIPAS-RL) in which each transmitter learns its payoff function, as well as the associated optimal covariance matrix strategies. Under the heterogeneous CODIPAS-RL, the transmitters can use different learning patterns (heterogeneous learning) and different learning rates. We provide sufficient conditions for the almost-sure convergence of the heterogeneous learning to ordinary differential equations. Extensions of the CODIPAS-RL to It's stochastic differential equations are discussed.

AB - In this paper, we study dynamic robust power-allocation games in multiple-input-multiple-output systems under the imperfectness of the channel-state information at the transmitters. Using a robust pseudopotential-game approach, we show the existence of robust solutions in both discrete and continuous action spaces under suitable conditions. Considering the imperfectness in terms of the payoff measurement at the transmitters, we propose a COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (CODIPAS-RL) in which each transmitter learns its payoff function, as well as the associated optimal covariance matrix strategies. Under the heterogeneous CODIPAS-RL, the transmitters can use different learning patterns (heterogeneous learning) and different learning rates. We provide sufficient conditions for the almost-sure convergence of the heterogeneous learning to ordinary differential equations. Extensions of the CODIPAS-RL to It's stochastic differential equations are discussed.

KW - Dynamic games

KW - learning

KW - multiple-input-multiple-output (MIMO)

KW - robust games

UR - http://www.scopus.com/inward/record.url?scp=79960698799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960698799&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2010.2102751

DO - 10.1109/TSMCB.2010.2102751

M3 - Article

AN - SCOPUS:79960698799

VL - 41

SP - 990

EP - 1002

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 4

M1 - 5699932

ER -