Matches in SemOpenAlex for { <https://semopenalex.org/work/W2116123258> ?p ?o ?g. }
- W2116123258 endingPage "234" @default.
- W2116123258 startingPage "213" @default.
- W2116123258 abstract "Simulation-based policy iteration (SBPI) is a modification of the policy iteration algorithm for computing optimal policies for Markov decision processes. At each iteration, rather than solving the average evaluation equations, SBPI employs simulation to estimate a solution to these equations. For recurrent average-reward Markov decision processes with finite state and action spaces, we provide easily verifiable conditions that ensure that simulation-based policy iteration almost-surely eventually never leaves the set of optimal decision rules. We analyze three simulation estimators for solutions to the average evaluation equations. Using our general results, we derive simple conditions on the simulation run lengths that guarantee the almost-sure convergence of the algorithm." @default.
- W2116123258 created "2016-06-24" @default.
- W2116123258 creator A5012592099 @default.
- W2116123258 creator A5032992144 @default.
- W2116123258 creator A5075933702 @default.
- W2116123258 date "2003-02-27" @default.
- W2116123258 modified "2023-10-01" @default.
- W2116123258 title "CONVERGENCE OF SIMULATION-BASED POLICY ITERATION" @default.
- W2116123258 cites W1497026160 @default.
- W2116123258 cites W1528477830 @default.
- W2116123258 cites W1540515733 @default.
- W2116123258 cites W1544193923 @default.
- W2116123258 cites W1576452626 @default.
- W2116123258 cites W184225095 @default.
- W2116123258 cites W1995713768 @default.
- W2116123258 cites W2021231433 @default.
- W2116123258 cites W2021469018 @default.
- W2116123258 cites W2028145673 @default.
- W2116123258 cites W2033900415 @default.
- W2116123258 cites W2035402840 @default.
- W2116123258 cites W2080631849 @default.
- W2116123258 cites W2082261506 @default.
- W2116123258 cites W2091565802 @default.
- W2116123258 cites W2098432798 @default.
- W2116123258 cites W2114202040 @default.
- W2116123258 cites W2119567691 @default.
- W2116123258 cites W2147750403 @default.
- W2116123258 cites W2152650468 @default.
- W2116123258 cites W2156150292 @default.
- W2116123258 cites W2171033527 @default.
- W2116123258 cites W2799087070 @default.
- W2116123258 cites W32403112 @default.
- W2116123258 doi "https://doi.org/10.1017/s0269964803172051" @default.
- W2116123258 hasPublicationYear "2003" @default.
- W2116123258 type Work @default.
- W2116123258 sameAs 2116123258 @default.
- W2116123258 citedByCount "27" @default.
- W2116123258 countsByYear W21161232582012 @default.
- W2116123258 countsByYear W21161232582013 @default.
- W2116123258 countsByYear W21161232582014 @default.
- W2116123258 countsByYear W21161232582015 @default.
- W2116123258 countsByYear W21161232582016 @default.
- W2116123258 countsByYear W21161232582017 @default.
- W2116123258 countsByYear W21161232582018 @default.
- W2116123258 countsByYear W21161232582019 @default.
- W2116123258 countsByYear W21161232582020 @default.
- W2116123258 countsByYear W21161232582022 @default.
- W2116123258 crossrefType "journal-article" @default.
- W2116123258 hasAuthorship W2116123258A5012592099 @default.
- W2116123258 hasAuthorship W2116123258A5032992144 @default.
- W2116123258 hasAuthorship W2116123258A5075933702 @default.
- W2116123258 hasBestOaLocation W21161232582 @default.
- W2116123258 hasConcept C105795698 @default.
- W2116123258 hasConcept C106189395 @default.
- W2116123258 hasConcept C111472728 @default.
- W2116123258 hasConcept C119857082 @default.
- W2116123258 hasConcept C126255220 @default.
- W2116123258 hasConcept C138885662 @default.
- W2116123258 hasConcept C159694833 @default.
- W2116123258 hasConcept C159886148 @default.
- W2116123258 hasConcept C162324750 @default.
- W2116123258 hasConcept C177264268 @default.
- W2116123258 hasConcept C185429906 @default.
- W2116123258 hasConcept C199360897 @default.
- W2116123258 hasConcept C2777303404 @default.
- W2116123258 hasConcept C2780586882 @default.
- W2116123258 hasConcept C28826006 @default.
- W2116123258 hasConcept C33923547 @default.
- W2116123258 hasConcept C41008148 @default.
- W2116123258 hasConcept C50522688 @default.
- W2116123258 hasConcept C85847156 @default.
- W2116123258 hasConcept C98763669 @default.
- W2116123258 hasConceptScore W2116123258C105795698 @default.
- W2116123258 hasConceptScore W2116123258C106189395 @default.
- W2116123258 hasConceptScore W2116123258C111472728 @default.
- W2116123258 hasConceptScore W2116123258C119857082 @default.
- W2116123258 hasConceptScore W2116123258C126255220 @default.
- W2116123258 hasConceptScore W2116123258C138885662 @default.
- W2116123258 hasConceptScore W2116123258C159694833 @default.
- W2116123258 hasConceptScore W2116123258C159886148 @default.
- W2116123258 hasConceptScore W2116123258C162324750 @default.
- W2116123258 hasConceptScore W2116123258C177264268 @default.
- W2116123258 hasConceptScore W2116123258C185429906 @default.
- W2116123258 hasConceptScore W2116123258C199360897 @default.
- W2116123258 hasConceptScore W2116123258C2777303404 @default.
- W2116123258 hasConceptScore W2116123258C2780586882 @default.
- W2116123258 hasConceptScore W2116123258C28826006 @default.
- W2116123258 hasConceptScore W2116123258C33923547 @default.
- W2116123258 hasConceptScore W2116123258C41008148 @default.
- W2116123258 hasConceptScore W2116123258C50522688 @default.
- W2116123258 hasConceptScore W2116123258C85847156 @default.
- W2116123258 hasConceptScore W2116123258C98763669 @default.
- W2116123258 hasIssue "2" @default.
- W2116123258 hasLocation W21161232581 @default.
- W2116123258 hasLocation W21161232582 @default.
- W2116123258 hasOpenAccess W2116123258 @default.
- W2116123258 hasPrimaryLocation W21161232581 @default.
- W2116123258 hasRelatedWork W124014347 @default.