Reverse Ishikawa-Nesterov Learning Scheme for Fractional Mean-Field Games

Research output: Contribution to journalArticle

Abstract

Reverse Ishikawa-Nesterov's algorithm is one of the speedup techniques for finding best response set in mean-field games. However, the convergence rate was not examined so far. In this work, we evaluate the convergence rate and convergence time of reverse Ishikawa-Nesterov learning scheme for a deterministic fractional mean-field games. The fractional mean-field game problem given by a fractional controlled state dynamics and payoff that measures the gap between a mean-field term and the fractional integral of the state. First, we prove that the problem is well-posed and has a unique best response to mean-field. Second, we derive conditions for convergence of the reverse Ishikawa-based learning scheme and provide the error gap. Finally, we show that the reverse Ishikawa-Nesterov's technique outperforms the standard descent methods.

Original languageEnglish (US)
Pages (from-to)8090-8096
Number of pages7
JournalIFAC-PapersOnLine
Volume50
Issue number1
DOIs
StatePublished - Jul 1 2017

Keywords

  • fractional order
  • game theory
  • mean-field
  • speedup learning

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Reverse Ishikawa-Nesterov Learning Scheme for Fractional Mean-Field Games. / Hamidou, Tembine.

In: IFAC-PapersOnLine, Vol. 50, No. 1, 01.07.2017, p. 8090-8096.

Research output: Contribution to journalArticle

@article{ee5b9e3ef2294f7688ce178174aa90c7,
title = "Reverse Ishikawa-Nesterov Learning Scheme for Fractional Mean-Field Games",
abstract = "Reverse Ishikawa-Nesterov's algorithm is one of the speedup techniques for finding best response set in mean-field games. However, the convergence rate was not examined so far. In this work, we evaluate the convergence rate and convergence time of reverse Ishikawa-Nesterov learning scheme for a deterministic fractional mean-field games. The fractional mean-field game problem given by a fractional controlled state dynamics and payoff that measures the gap between a mean-field term and the fractional integral of the state. First, we prove that the problem is well-posed and has a unique best response to mean-field. Second, we derive conditions for convergence of the reverse Ishikawa-based learning scheme and provide the error gap. Finally, we show that the reverse Ishikawa-Nesterov's technique outperforms the standard descent methods.",
keywords = "fractional order, game theory, mean-field, speedup learning",
author = "Tembine Hamidou",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.ifacol.2017.08.1244",
language = "English (US)",
volume = "50",
pages = "8090--8096",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "1",

}

TY - JOUR

T1 - Reverse Ishikawa-Nesterov Learning Scheme for Fractional Mean-Field Games

AU - Hamidou, Tembine

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Reverse Ishikawa-Nesterov's algorithm is one of the speedup techniques for finding best response set in mean-field games. However, the convergence rate was not examined so far. In this work, we evaluate the convergence rate and convergence time of reverse Ishikawa-Nesterov learning scheme for a deterministic fractional mean-field games. The fractional mean-field game problem given by a fractional controlled state dynamics and payoff that measures the gap between a mean-field term and the fractional integral of the state. First, we prove that the problem is well-posed and has a unique best response to mean-field. Second, we derive conditions for convergence of the reverse Ishikawa-based learning scheme and provide the error gap. Finally, we show that the reverse Ishikawa-Nesterov's technique outperforms the standard descent methods.

AB - Reverse Ishikawa-Nesterov's algorithm is one of the speedup techniques for finding best response set in mean-field games. However, the convergence rate was not examined so far. In this work, we evaluate the convergence rate and convergence time of reverse Ishikawa-Nesterov learning scheme for a deterministic fractional mean-field games. The fractional mean-field game problem given by a fractional controlled state dynamics and payoff that measures the gap between a mean-field term and the fractional integral of the state. First, we prove that the problem is well-posed and has a unique best response to mean-field. Second, we derive conditions for convergence of the reverse Ishikawa-based learning scheme and provide the error gap. Finally, we show that the reverse Ishikawa-Nesterov's technique outperforms the standard descent methods.

KW - fractional order

KW - game theory

KW - mean-field

KW - speedup learning

UR - http://www.scopus.com/inward/record.url?scp=85031827099&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031827099&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2017.08.1244

DO - 10.1016/j.ifacol.2017.08.1244

M3 - Article

AN - SCOPUS:85031827099

VL - 50

SP - 8090

EP - 8096

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 1

ER -