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

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<rdf:Description>
<dc:creator>Guo, Junyi</dc:creator>
<dc:creator>International Actuarial Association</dc:creator>
<dc:date>2026-01-15</dc:date>
<dc:description xml:lang="es">Sumario: This 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</dc:description>
<dc:identifier>https://documentacion.fundacionmapfre.org/documentacion/publico/es/bib/189424.do</dc:identifier>
<dc:language>eng</dc:language>
<dc:rights xml:lang="es">InC - http://rightsstatements.org/vocab/InC/1.0/</dc:rights>
<dc:subject xml:lang="es">Mercados financieros</dc:subject>
<dc:subject xml:lang="es">Gestión de riesgos</dc:subject>
<dc:subject xml:lang="es">Modelo estocástico</dc:subject>
<dc:subject xml:lang="es">Modelo Gaussiano</dc:subject>
<dc:subject xml:lang="es">Cálculo actuarial</dc:subject>
<dc:subject xml:lang="es">Matemática del seguro</dc:subject>
<dc:subject xml:lang="es">Modelos matemáticos</dc:subject>
<dc:type xml:lang="es">Artículos y capítulos</dc:type>
<dc:title xml:lang="es">A Nonzero-sum game with reinforcement learning under mean-variance framework</dc:title>
<dc:relation xml:lang="es">En: Astin bulletin. - Belgium : ASTIN and AFIR Sections of the International Actuarial Association = ISSN 0515-0361. - 19/01/2026 Volume 56 Issue 1 - January 2026 , p. 154 - 180</dc:relation>
</rdf:Description>
</rdf:RDF>