FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048894195> ?p ?o ?g. }

• W3048894195 abstract "Stochastic differential games have been used extensively to model agents' competitions in Finance, for instance, in P2P lending platforms from the Fintech industry, the banking system for systemic risk, and insurance markets. The recently proposed machine learning algorithm, deep fictitious play, provides a novel efficient tool for finding Markovian Nash equilibrium of large $N$-player asymmetric stochastic differential games [J. Han and R. Hu, Mathematical and Scientific Machine Learning Conference, pages 221-245, PMLR, 2020]. By incorporating the idea of fictitious play, the algorithm decouples the game into $N$ sub-optimization problems, and identifies each player's optimal strategy with the deep backward stochastic differential equation (BSDE) method parallelly and repeatedly. In this paper, we prove the convergence of deep fictitious play (DFP) to the true Nash equilibrium. We can also show that the strategy based on DFP forms an $eps$-Nash equilibrium. We generalize the algorithm by proposing a new approach to decouple the games, and present numerical results of large population games showing the empirical convergence of the algorithm beyond the technical assumptions in the theorems." @default.
• W3048894195 created "2020-08-18" @default.
• W3048894195 creator A5017947325 @default.
• W3048894195 creator A5058618644 @default.
• W3048894195 creator A5090400461 @default.
• W3048894195 date "2020-08-12" @default.
• W3048894195 modified "2023-09-27" @default.
• W3048894195 title "Convergence of Deep Fictitious Play for Stochastic Differential Games" @default.
• W3048894195 cites W1015133923 @default.
• W3048894195 cites W1575104486 @default.
• W3048894195 cites W1581842928 @default.
• W3048894195 cites W1659904137 @default.
• W3048894195 cites W1836465849 @default.
• W3048894195 cites W1963798578 @default.
• W3048894195 cites W1975076156 @default.
• W3048894195 cites W1993228970 @default.
• W3048894195 cites W1994791309 @default.
• W3048894195 cites W2015541347 @default.
• W3048894195 cites W2028145673 @default.
• W3048894195 cites W2043635114 @default.
• W3048894195 cites W2044287460 @default.
• W3048894195 cites W2067399933 @default.
• W3048894195 cites W2078895915 @default.
• W3048894195 cites W2081458347 @default.
• W3048894195 cites W2086924628 @default.
• W3048894195 cites W2088509323 @default.
• W3048894195 cites W2096913736 @default.
• W3048894195 cites W2118247617 @default.
• W3048894195 cites W2119567691 @default.
• W3048894195 cites W2121494316 @default.
• W3048894195 cites W2142850237 @default.
• W3048894195 cites W2157883119 @default.
• W3048894195 cites W2265105391 @default.
• W3048894195 cites W2551937961 @default.
• W3048894195 cites W2610414461 @default.
• W3048894195 cites W2625995436 @default.
• W3048894195 cites W2739748921 @default.
• W3048894195 cites W2749028154 @default.
• W3048894195 cites W2767824837 @default.
• W3048894195 cites W2791784110 @default.
• W3048894195 cites W2793149742 @default.
• W3048894195 cites W2892501771 @default.
• W3048894195 cites W2899507754 @default.
• W3048894195 cites W2924879216 @default.
• W3048894195 cites W2941095974 @default.
• W3048894195 cites W2943928526 @default.
• W3048894195 cites W2954388788 @default.
• W3048894195 cites W2955291419 @default.
• W3048894195 cites W2962879692 @default.
• W3048894195 cites W2963027742 @default.
• W3048894195 cites W2963585518 @default.
• W3048894195 cites W2964121744 @default.
• W3048894195 cites W2966737396 @default.
• W3048894195 cites W2970620827 @default.
• W3048894195 cites W2993551995 @default.
• W3048894195 cites W2997345668 @default.
• W3048894195 cites W3004547276 @default.
• W3048894195 cites W3004573026 @default.
• W3048894195 cites W3020277283 @default.
• W3048894195 cites W3022782115 @default.
• W3048894195 cites W3028529071 @default.
• W3048894195 cites W3033272935 @default.
• W3048894195 cites W3038093235 @default.
• W3048894195 cites W3112730052 @default.
• W3048894195 cites W3121382465 @default.
• W3048894195 cites W3122906764 @default.
• W3048894195 cites W3124751568 @default.
• W3048894195 cites W3150654747 @default.
• W3048894195 cites W316323024 @default.
• W3048894195 cites W3200565419 @default.
• W3048894195 cites W2746521622 @default.
• W3048894195 cites W3203535929 @default.
• W3048894195 doi "https://doi.org/10.48550/arxiv.2008.05519" @default.
• W3048894195 hasPublicationYear "2020" @default.
• W3048894195 type Work @default.
• W3048894195 sameAs 3048894195 @default.
• W3048894195 citedByCount "8" @default.
• W3048894195 countsByYear W30488941952019 @default.
• W3048894195 countsByYear W30488941952020 @default.
• W3048894195 countsByYear W30488941952021 @default.
• W3048894195 crossrefType "posted-content" @default.
• W3048894195 hasAuthorship W3048894195A5017947325 @default.
• W3048894195 hasAuthorship W3048894195A5058618644 @default.
• W3048894195 hasAuthorship W3048894195A5090400461 @default.
• W3048894195 hasBestOaLocation W30488941951 @default.
• W3048894195 hasConcept C126255220 @default.
• W3048894195 hasConcept C127413603 @default.
• W3048894195 hasConcept C144237770 @default.
• W3048894195 hasConcept C145071142 @default.
• W3048894195 hasConcept C146978453 @default.
• W3048894195 hasConcept C162324750 @default.
• W3048894195 hasConcept C2777303404 @default.
• W3048894195 hasConcept C28826006 @default.
• W3048894195 hasConcept C32407928 @default.
• W3048894195 hasConcept C33923547 @default.
• W3048894195 hasConcept C41008148 @default.
• W3048894195 hasConcept C46814582 @default.
• W3048894195 hasConcept C50522688 @default.
• W3048894195 hasConcept C51955184 @default.
• W3048894195 hasConcept C93226319 @default.

• next