Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014321323> ?p ?o ?g. }
- W3014321323 abstract "In this paper, we consider a finite horizon, non-stationary, mean field games (MFG) with a large population of homogeneous players, sequentially making strategic decisions, where each player is affected by other players through an aggregate population state termed as mean field state. Each player has a private type that only it can observe, and a mean field population state representing the empirical distribution of other players' types, which is shared among all of them. Recently, authors in [1] provided a sequential decomposition algorithm to compute mean field equilibrium (MFE) for such games which allows for the computation of equilibrium policies for them in linear time than exponential, as before. In this paper, we extend it for the case when state transitions are not known, to propose a reinforcement learning algorithm based on Expected Sarsa with a policy gradient approach that learns the MFE policy by learning the dynamics of the game simultaneously. We illustrate our results using cyber-physical security example." @default.
- W3014321323 created "2020-04-10" @default.
- W3014321323 creator A5035299142 @default.
- W3014321323 creator A5045766079 @default.
- W3014321323 creator A5088120102 @default.
- W3014321323 date "2020-04-05" @default.
- W3014321323 modified "2023-09-27" @default.
- W3014321323 title "Model-free Reinforcement Learning for Non-stationary Mean Field Games" @default.
- W3014321323 cites W1481965470 @default.
- W3014321323 cites W1991888757 @default.
- W3014321323 cites W2011000015 @default.
- W3014321323 cites W2038686546 @default.
- W3014321323 cites W2100752967 @default.
- W3014321323 cites W2131832787 @default.
- W3014321323 cites W2570640613 @default.
- W3014321323 cites W2581988916 @default.
- W3014321323 cites W2783327422 @default.
- W3014321323 cites W2785315072 @default.
- W3014321323 cites W2944347018 @default.
- W3014321323 cites W2945395894 @default.
- W3014321323 cites W2947846187 @default.
- W3014321323 cites W2955291419 @default.
- W3014321323 cites W2970875146 @default.
- W3014321323 hasPublicationYear "2020" @default.
- W3014321323 type Work @default.
- W3014321323 sameAs 3014321323 @default.
- W3014321323 citedByCount "0" @default.
- W3014321323 crossrefType "posted-content" @default.
- W3014321323 hasAuthorship W3014321323A5035299142 @default.
- W3014321323 hasAuthorship W3014321323A5045766079 @default.
- W3014321323 hasAuthorship W3014321323A5088120102 @default.
- W3014321323 hasConcept C11413529 @default.
- W3014321323 hasConcept C121332964 @default.
- W3014321323 hasConcept C126255220 @default.
- W3014321323 hasConcept C126285488 @default.
- W3014321323 hasConcept C144024400 @default.
- W3014321323 hasConcept C144237770 @default.
- W3014321323 hasConcept C145071142 @default.
- W3014321323 hasConcept C149923435 @default.
- W3014321323 hasConcept C154945302 @default.
- W3014321323 hasConcept C162324750 @default.
- W3014321323 hasConcept C202213908 @default.
- W3014321323 hasConcept C202444582 @default.
- W3014321323 hasConcept C203379541 @default.
- W3014321323 hasConcept C2908647359 @default.
- W3014321323 hasConcept C33923547 @default.
- W3014321323 hasConcept C41008148 @default.
- W3014321323 hasConcept C45374587 @default.
- W3014321323 hasConcept C46814582 @default.
- W3014321323 hasConcept C48103436 @default.
- W3014321323 hasConcept C556758197 @default.
- W3014321323 hasConcept C62520636 @default.
- W3014321323 hasConcept C89967458 @default.
- W3014321323 hasConcept C9652623 @default.
- W3014321323 hasConcept C97541855 @default.
- W3014321323 hasConceptScore W3014321323C11413529 @default.
- W3014321323 hasConceptScore W3014321323C121332964 @default.
- W3014321323 hasConceptScore W3014321323C126255220 @default.
- W3014321323 hasConceptScore W3014321323C126285488 @default.
- W3014321323 hasConceptScore W3014321323C144024400 @default.
- W3014321323 hasConceptScore W3014321323C144237770 @default.
- W3014321323 hasConceptScore W3014321323C145071142 @default.
- W3014321323 hasConceptScore W3014321323C149923435 @default.
- W3014321323 hasConceptScore W3014321323C154945302 @default.
- W3014321323 hasConceptScore W3014321323C162324750 @default.
- W3014321323 hasConceptScore W3014321323C202213908 @default.
- W3014321323 hasConceptScore W3014321323C202444582 @default.
- W3014321323 hasConceptScore W3014321323C203379541 @default.
- W3014321323 hasConceptScore W3014321323C2908647359 @default.
- W3014321323 hasConceptScore W3014321323C33923547 @default.
- W3014321323 hasConceptScore W3014321323C41008148 @default.
- W3014321323 hasConceptScore W3014321323C45374587 @default.
- W3014321323 hasConceptScore W3014321323C46814582 @default.
- W3014321323 hasConceptScore W3014321323C48103436 @default.
- W3014321323 hasConceptScore W3014321323C556758197 @default.
- W3014321323 hasConceptScore W3014321323C62520636 @default.
- W3014321323 hasConceptScore W3014321323C89967458 @default.
- W3014321323 hasConceptScore W3014321323C9652623 @default.
- W3014321323 hasConceptScore W3014321323C97541855 @default.
- W3014321323 hasLocation W30143213231 @default.
- W3014321323 hasOpenAccess W3014321323 @default.
- W3014321323 hasPrimaryLocation W30143213231 @default.
- W3014321323 hasRelatedWork W1489458588 @default.
- W3014321323 hasRelatedWork W1569077671 @default.
- W3014321323 hasRelatedWork W2116796800 @default.
- W3014321323 hasRelatedWork W2570640613 @default.
- W3014321323 hasRelatedWork W2581988916 @default.
- W3014321323 hasRelatedWork W2589043502 @default.
- W3014321323 hasRelatedWork W2783327422 @default.
- W3014321323 hasRelatedWork W2888320502 @default.
- W3014321323 hasRelatedWork W2945395894 @default.
- W3014321323 hasRelatedWork W2955291419 @default.
- W3014321323 hasRelatedWork W2964002079 @default.
- W3014321323 hasRelatedWork W2964982781 @default.
- W3014321323 hasRelatedWork W2995185709 @default.
- W3014321323 hasRelatedWork W3012364697 @default.
- W3014321323 hasRelatedWork W3082540285 @default.
- W3014321323 hasRelatedWork W3089675514 @default.
- W3014321323 hasRelatedWork W3092283217 @default.
- W3014321323 hasRelatedWork W3116313901 @default.