Payoff measurement noise in risk-sensitive mean-field-type games

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

Abstract

Payoff measurement noise constitutes a major problem in practical interactive decision-making scenarios. When agent's payoff is erroneously perceived or observed with a noise functional, the response is highly impacted. In this paper, a risk-sensitive approach is proposed for capturing players' behaviors in presence of measurement randomness in mean-field-type games. Equilibrium and optimal strategy systems are established using stochastic maximum principle and dynamic programming principle in infinite dimensions.

Original languageEnglish (US)
Title of host publicationProceedings of the 29th Chinese Control and Decision Conference, CCDC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3764-3769
Number of pages6
ISBN (Electronic)9781509046560
DOIs
StatePublished - Jul 12 2017
Event29th Chinese Control and Decision Conference, CCDC 2017 - Chongqing, China
Duration: May 28 2017May 30 2017

Other

Other29th Chinese Control and Decision Conference, CCDC 2017
CountryChina
CityChongqing
Period5/28/175/30/17

Fingerprint

Mean Field
Game
Dynamic Programming Principle
Infinite Dimensions
Optimal Strategy
Maximum Principle
Randomness
Decision Making
Scenarios
Optimal strategy
Dynamic programming
Maximum principle
Decision making

Keywords

  • Dynamic programming
  • Game theory
  • Mean-field
  • Stochastic control
  • Stochastic maximum principle

ASJC Scopus subject areas

  • Decision Sciences (miscellaneous)
  • Control and Optimization

Cite this

Hamidou, T. (2017). Payoff measurement noise in risk-sensitive mean-field-type games. In Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017 (pp. 3764-3769). [7979159] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCDC.2017.7979159

Payoff measurement noise in risk-sensitive mean-field-type games. / Hamidou, Tembine.

Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3764-3769 7979159.

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

Hamidou, T 2017, Payoff measurement noise in risk-sensitive mean-field-type games. in Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017., 7979159, Institute of Electrical and Electronics Engineers Inc., pp. 3764-3769, 29th Chinese Control and Decision Conference, CCDC 2017, Chongqing, China, 5/28/17. https://doi.org/10.1109/CCDC.2017.7979159
Hamidou T. Payoff measurement noise in risk-sensitive mean-field-type games. In Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 3764-3769. 7979159 https://doi.org/10.1109/CCDC.2017.7979159
Hamidou, Tembine. / Payoff measurement noise in risk-sensitive mean-field-type games. Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 3764-3769
@inproceedings{04f09b97579f4cfb82f202b2afd0b40d,
title = "Payoff measurement noise in risk-sensitive mean-field-type games",
abstract = "Payoff measurement noise constitutes a major problem in practical interactive decision-making scenarios. When agent's payoff is erroneously perceived or observed with a noise functional, the response is highly impacted. In this paper, a risk-sensitive approach is proposed for capturing players' behaviors in presence of measurement randomness in mean-field-type games. Equilibrium and optimal strategy systems are established using stochastic maximum principle and dynamic programming principle in infinite dimensions.",
keywords = "Dynamic programming, Game theory, Mean-field, Stochastic control, Stochastic maximum principle",
author = "Tembine Hamidou",
year = "2017",
month = "7",
day = "12",
doi = "10.1109/CCDC.2017.7979159",
language = "English (US)",
pages = "3764--3769",
booktitle = "Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Payoff measurement noise in risk-sensitive mean-field-type games

AU - Hamidou, Tembine

PY - 2017/7/12

Y1 - 2017/7/12

N2 - Payoff measurement noise constitutes a major problem in practical interactive decision-making scenarios. When agent's payoff is erroneously perceived or observed with a noise functional, the response is highly impacted. In this paper, a risk-sensitive approach is proposed for capturing players' behaviors in presence of measurement randomness in mean-field-type games. Equilibrium and optimal strategy systems are established using stochastic maximum principle and dynamic programming principle in infinite dimensions.

AB - Payoff measurement noise constitutes a major problem in practical interactive decision-making scenarios. When agent's payoff is erroneously perceived or observed with a noise functional, the response is highly impacted. In this paper, a risk-sensitive approach is proposed for capturing players' behaviors in presence of measurement randomness in mean-field-type games. Equilibrium and optimal strategy systems are established using stochastic maximum principle and dynamic programming principle in infinite dimensions.

KW - Dynamic programming

KW - Game theory

KW - Mean-field

KW - Stochastic control

KW - Stochastic maximum principle

UR - http://www.scopus.com/inward/record.url?scp=85028051062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028051062&partnerID=8YFLogxK

U2 - 10.1109/CCDC.2017.7979159

DO - 10.1109/CCDC.2017.7979159

M3 - Conference contribution

AN - SCOPUS:85028051062

SP - 3764

EP - 3769

BT - Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -