Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951478739> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2951478739 abstract "We investigate a class of reinforcement learning dynamics where players adjust their strategies based on their actions' cumulative payoffs over time - specifically, by playing mixed strategies that maximize their expected cumulative payoff minus a regularization term. A widely studied example is exponential reinforcement learning, a process induced by an entropic regularization term which leads mixed strategies to evolve according to the replicator dynamics. However, in contrast to the class of regularization functions used to define smooth best responses in models of stochastic fictitious play, the functions used in this paper need not be infinitely steep at the boundary of the simplex; in fact, dropping this requirement gives rise to an important dichotomy between steep and nonsteep cases. In this general framework, we extend several properties of exponential learning, including the elimination of dominated strategies, the asymptotic stability of strict Nash equilibria, and the convergence of time-averaged trajectories in zero-sum games with an interior Nash equilibrium." @default.
- W2951478739 created "2019-06-27" @default.
- W2951478739 creator A5017369526 @default.
- W2951478739 creator A5018966648 @default.
- W2951478739 date "2014-07-23" @default.
- W2951478739 modified "2023-09-25" @default.
- W2951478739 title "Learning in games via reinforcement and regularization" @default.
- W2951478739 hasPublicationYear "2014" @default.
- W2951478739 type Work @default.
- W2951478739 sameAs 2951478739 @default.
- W2951478739 citedByCount "1" @default.
- W2951478739 countsByYear W29514787392016 @default.
- W2951478739 crossrefType "posted-content" @default.
- W2951478739 hasAuthorship W2951478739A5017369526 @default.
- W2951478739 hasAuthorship W2951478739A5018966648 @default.
- W2951478739 hasConcept C121332964 @default.
- W2951478739 hasConcept C126255220 @default.
- W2951478739 hasConcept C134306372 @default.
- W2951478739 hasConcept C144024400 @default.
- W2951478739 hasConcept C144237770 @default.
- W2951478739 hasConcept C145071142 @default.
- W2951478739 hasConcept C149923435 @default.
- W2951478739 hasConcept C151376022 @default.
- W2951478739 hasConcept C154945302 @default.
- W2951478739 hasConcept C158622935 @default.
- W2951478739 hasConcept C167964875 @default.
- W2951478739 hasConcept C22171661 @default.
- W2951478739 hasConcept C2776135515 @default.
- W2951478739 hasConcept C2777212361 @default.
- W2951478739 hasConcept C28826006 @default.
- W2951478739 hasConcept C2908647359 @default.
- W2951478739 hasConcept C32407928 @default.
- W2951478739 hasConcept C33923547 @default.
- W2951478739 hasConcept C41008148 @default.
- W2951478739 hasConcept C46814582 @default.
- W2951478739 hasConcept C50318809 @default.
- W2951478739 hasConcept C62520636 @default.
- W2951478739 hasConcept C97541855 @default.
- W2951478739 hasConceptScore W2951478739C121332964 @default.
- W2951478739 hasConceptScore W2951478739C126255220 @default.
- W2951478739 hasConceptScore W2951478739C134306372 @default.
- W2951478739 hasConceptScore W2951478739C144024400 @default.
- W2951478739 hasConceptScore W2951478739C144237770 @default.
- W2951478739 hasConceptScore W2951478739C145071142 @default.
- W2951478739 hasConceptScore W2951478739C149923435 @default.
- W2951478739 hasConceptScore W2951478739C151376022 @default.
- W2951478739 hasConceptScore W2951478739C154945302 @default.
- W2951478739 hasConceptScore W2951478739C158622935 @default.
- W2951478739 hasConceptScore W2951478739C167964875 @default.
- W2951478739 hasConceptScore W2951478739C22171661 @default.
- W2951478739 hasConceptScore W2951478739C2776135515 @default.
- W2951478739 hasConceptScore W2951478739C2777212361 @default.
- W2951478739 hasConceptScore W2951478739C28826006 @default.
- W2951478739 hasConceptScore W2951478739C2908647359 @default.
- W2951478739 hasConceptScore W2951478739C32407928 @default.
- W2951478739 hasConceptScore W2951478739C33923547 @default.
- W2951478739 hasConceptScore W2951478739C41008148 @default.
- W2951478739 hasConceptScore W2951478739C46814582 @default.
- W2951478739 hasConceptScore W2951478739C50318809 @default.
- W2951478739 hasConceptScore W2951478739C62520636 @default.
- W2951478739 hasConceptScore W2951478739C97541855 @default.
- W2951478739 hasLocation W29514787391 @default.
- W2951478739 hasOpenAccess W2951478739 @default.
- W2951478739 hasPrimaryLocation W29514787391 @default.
- W2951478739 hasRelatedWork W1679223795 @default.
- W2951478739 hasRelatedWork W1967250398 @default.
- W2951478739 hasRelatedWork W1968394721 @default.
- W2951478739 hasRelatedWork W2034928886 @default.
- W2951478739 hasRelatedWork W2067018002 @default.
- W2951478739 hasRelatedWork W2097866252 @default.
- W2951478739 hasRelatedWork W2120846115 @default.
- W2951478739 hasRelatedWork W2141828543 @default.
- W2951478739 hasRelatedWork W2243419840 @default.
- W2951478739 hasRelatedWork W2270300680 @default.
- W2951478739 hasRelatedWork W2744733630 @default.
- W2951478739 hasRelatedWork W2783096200 @default.
- W2951478739 hasRelatedWork W2893314716 @default.
- W2951478739 hasRelatedWork W2981553829 @default.
- W2951478739 hasRelatedWork W2995824757 @default.
- W2951478739 hasRelatedWork W3109452493 @default.
- W2951478739 hasRelatedWork W3116477934 @default.
- W2951478739 hasRelatedWork W3124449095 @default.
- W2951478739 hasRelatedWork W3196517148 @default.
- W2951478739 hasRelatedWork W3200627097 @default.
- W2951478739 isParatext "false" @default.
- W2951478739 isRetracted "false" @default.
- W2951478739 magId "2951478739" @default.
- W2951478739 workType "article" @default.