Search

A Nonzero-sum game with reinforcement learning under mean-variance framework

Portada
MARC record
Tag12Value
LDR  00000cab a2200000 4500
001  MAP20260001968
003  MAP
005  20260205101750.0
008  260202e20260115bel|||p |0|||b|eng d
040  ‎$a‎MAP‎$b‎spa‎$d‎MAP
084  ‎$a‎6
24512‎$a‎A Nonzero-sum game with reinforcement learning under mean-variance framework‎$c‎Junyi Guo...[et al.]
520  ‎$a‎This paper examines a competitive setting in which two agents invest in a risk-free and a risky asset while considering both their own wealth and their wealth gap relative to each other. With market parameters partially or fully unknown, the problem is formulated as a nonzero-sum differential game within a reinforcement learning framework. Each agent seeks to optimize a Choquet-regularized, time-inconsistent mean-variance objective. Using dynamic programming, the authors derive a time-consistent Nash equilibrium in an incomplete market. Under a Gaussian mean-return assumption, they obtain an explicit analytical solution that enables the construction of a practical reinforcement learning algorithm. The algorithm shows uniform convergence, despite the absence of a traditional policy-improvement guarantee, and numerical experiments confirm its robustness and effectiveness
650 4‎$0‎MAPA20080597641‎$a‎Mercados financieros
650 4‎$0‎MAPA20250003316‎$a‎Gestión de riesgos
650 4‎$0‎MAPA20080586447‎$a‎Modelo estocástico
650 4‎$0‎MAPA20080576790‎$a‎Modelo Gaussiano
650 4‎$0‎MAPA20080579258‎$a‎Cálculo actuarial
650 4‎$0‎MAPA20080602437‎$a‎Matemática del seguro
650 4‎$0‎MAPA20080592042‎$a‎Modelos matemáticos
7001 ‎$0‎MAPA20080649876‎$a‎Guo, Junyi
7102 ‎$0‎MAPA20100017661‎$a‎International Actuarial Association
7730 ‎$w‎MAP20077000420‎$g‎19/01/2026 Volume 56 Issue 1 - January 2026 , p. 154 - 180‎$x‎0515-0361‎$t‎Astin bulletin‎$d‎Belgium : ASTIN and AFIR Sections of the International Actuarial Association