Back to Search

Learning mean-field games with discounted and average costs

Title	Learning mean-field games with discounted and average costs
Author	Anahtarcı, Berkay, Karıksız, Can Deha, Saldı, N.
Publication Date:	2023
Publication Place	- Microtome Publishing
Subject	Mean-field games, Approximate Nash equilibrium, Fitted Q-iteration algo-rithm, Discounted-cost, Average-cost
Type	Periodical
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	1532-4435
Record ID	7f13317e-b850-4640-af22-2d16f8fdc921
Library Location	Natural and Mathematical Sciences
Date	2023
Notes	TÜBİTAK
Sample Text	We consider learning approximate Nash equilibria for discrete-time mean-field games with stochastic nonlinear state dynamics subject to both average and discounted costs. To this end, we introduce a mean-field equilibrium (MFE) operator, whose fixed point is a mean-field equilibrium, i.e., equilibrium in the infinite population limit. We first prove that this operator is a contraction, and propose a learning algorithm to compute an approximate mean-field equilibrium by approximating the MFE operator with a random one. Moreover, using the contraction property of the MFE operator, we establish the error analysis of the proposed learning algorithm. We then show that the learned mean-field equilibrium constitutes an approximate Nash equilibrium for finite-agent games.
Cilt	24

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

Learning mean-field games with discounted and average costs

Author Anahtarcı, Berkay, Karıksız, Can Deha, Saldı, N.

Publication Date 2023

Publication Place - Microtome Publishing

Subject Mean-field games, Approximate Nash equilibrium, Fitted Q-iteration algo-rithm, Discounted-cost, Average-cost

Type Periodical

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 1532-4435

Record ID 7f13317e-b850-4640-af22-2d16f8fdc921

Library Location Natural and Mathematical Sciences

Date 2023

Notes TÜBİTAK

Sample Text We consider learning approximate Nash equilibria for discrete-time mean-field games with stochastic nonlinear state dynamics subject to both average and discounted costs. To this end, we introduce a mean-field equilibrium (MFE) operator, whose fixed point is a mean-field equilibrium, i.e., equilibrium in the infinite population limit. We first prove that this operator is a contraction, and propose a learning algorithm to compute an approximate mean-field equilibrium by approximating the MFE operator with a random one. Moreover, using the contraction property of the MFE operator, we establish the error analysis of the proposed learning algorithm. We then show that the learned mean-field equilibrium constitutes an approximate Nash equilibrium for finite-agent games.

Cilt 24