Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149920308> ?p ?o ?g. }
- W3149920308 endingPage "104899" @default.
- W3149920308 startingPage "104899" @default.
- W3149920308 abstract "In this letter we provide several informative tight error bounds when using value function approximators for the risk-sensitive cost setting for a given policy represented using exponential utility. The novelty of our approach is that we make use of the irreducibility of the underlying Markov chain (resulting in better bounds using Perron–Frobenius eigenvectors) to derive new bounds whereas the earlier work used primarily the spectral variation bound which holds for any matrix, hence did not make use of the irreducibility. All our bounds have a perturbation term for large state spaces. We also present examples where we show that the new bounds perform 90-100% better than the earlier proposed spectral variation bound." @default.
- W3149920308 created "2021-04-13" @default.
- W3149920308 creator A5015304170 @default.
- W3149920308 creator A5038163398 @default.
- W3149920308 date "2021-04-01" @default.
- W3149920308 modified "2023-09-27" @default.
- W3149920308 title "On tight bounds for function approximation error in risk-sensitive reinforcement learning" @default.
- W3149920308 cites W1990437501 @default.
- W3149920308 cites W1997394097 @default.
- W3149920308 cites W2001009060 @default.
- W3149920308 cites W2016442431 @default.
- W3149920308 cites W2027106436 @default.
- W3149920308 cites W2071736481 @default.
- W3149920308 cites W2086304253 @default.
- W3149920308 cites W2120465407 @default.
- W3149920308 cites W2139914196 @default.
- W3149920308 cites W2146524676 @default.
- W3149920308 cites W2579539833 @default.
- W3149920308 cites W4244963780 @default.
- W3149920308 doi "https://doi.org/10.1016/j.sysconle.2021.104899" @default.
- W3149920308 hasPublicationYear "2021" @default.
- W3149920308 type Work @default.
- W3149920308 sameAs 3149920308 @default.
- W3149920308 citedByCount "1" @default.
- W3149920308 countsByYear W31499203082023 @default.
- W3149920308 crossrefType "journal-article" @default.
- W3149920308 hasAuthorship W3149920308A5015304170 @default.
- W3149920308 hasAuthorship W3149920308A5038163398 @default.
- W3149920308 hasConcept C105795698 @default.
- W3149920308 hasConcept C106487976 @default.
- W3149920308 hasConcept C118615104 @default.
- W3149920308 hasConcept C121332964 @default.
- W3149920308 hasConcept C126255220 @default.
- W3149920308 hasConcept C134306372 @default.
- W3149920308 hasConcept C138885662 @default.
- W3149920308 hasConcept C14036430 @default.
- W3149920308 hasConcept C151376022 @default.
- W3149920308 hasConcept C154945302 @default.
- W3149920308 hasConcept C158693339 @default.
- W3149920308 hasConcept C159985019 @default.
- W3149920308 hasConcept C177918212 @default.
- W3149920308 hasConcept C192562407 @default.
- W3149920308 hasConcept C202444582 @default.
- W3149920308 hasConcept C27206212 @default.
- W3149920308 hasConcept C2776823524 @default.
- W3149920308 hasConcept C2778738651 @default.
- W3149920308 hasConcept C28826006 @default.
- W3149920308 hasConcept C33923547 @default.
- W3149920308 hasConcept C41008148 @default.
- W3149920308 hasConcept C62520636 @default.
- W3149920308 hasConcept C77553402 @default.
- W3149920308 hasConcept C78458016 @default.
- W3149920308 hasConcept C86803240 @default.
- W3149920308 hasConcept C97541855 @default.
- W3149920308 hasConcept C98763669 @default.
- W3149920308 hasConceptScore W3149920308C105795698 @default.
- W3149920308 hasConceptScore W3149920308C106487976 @default.
- W3149920308 hasConceptScore W3149920308C118615104 @default.
- W3149920308 hasConceptScore W3149920308C121332964 @default.
- W3149920308 hasConceptScore W3149920308C126255220 @default.
- W3149920308 hasConceptScore W3149920308C134306372 @default.
- W3149920308 hasConceptScore W3149920308C138885662 @default.
- W3149920308 hasConceptScore W3149920308C14036430 @default.
- W3149920308 hasConceptScore W3149920308C151376022 @default.
- W3149920308 hasConceptScore W3149920308C154945302 @default.
- W3149920308 hasConceptScore W3149920308C158693339 @default.
- W3149920308 hasConceptScore W3149920308C159985019 @default.
- W3149920308 hasConceptScore W3149920308C177918212 @default.
- W3149920308 hasConceptScore W3149920308C192562407 @default.
- W3149920308 hasConceptScore W3149920308C202444582 @default.
- W3149920308 hasConceptScore W3149920308C27206212 @default.
- W3149920308 hasConceptScore W3149920308C2776823524 @default.
- W3149920308 hasConceptScore W3149920308C2778738651 @default.
- W3149920308 hasConceptScore W3149920308C28826006 @default.
- W3149920308 hasConceptScore W3149920308C33923547 @default.
- W3149920308 hasConceptScore W3149920308C41008148 @default.
- W3149920308 hasConceptScore W3149920308C62520636 @default.
- W3149920308 hasConceptScore W3149920308C77553402 @default.
- W3149920308 hasConceptScore W3149920308C78458016 @default.
- W3149920308 hasConceptScore W3149920308C86803240 @default.
- W3149920308 hasConceptScore W3149920308C97541855 @default.
- W3149920308 hasConceptScore W3149920308C98763669 @default.
- W3149920308 hasFunder F4320310071 @default.
- W3149920308 hasFunder F4320320719 @default.
- W3149920308 hasFunder F4320334035 @default.
- W3149920308 hasLocation W31499203081 @default.
- W3149920308 hasOpenAccess W3149920308 @default.
- W3149920308 hasPrimaryLocation W31499203081 @default.
- W3149920308 hasRelatedWork W1994932819 @default.
- W3149920308 hasRelatedWork W2025931822 @default.
- W3149920308 hasRelatedWork W2083193613 @default.
- W3149920308 hasRelatedWork W2229609461 @default.
- W3149920308 hasRelatedWork W2236072206 @default.
- W3149920308 hasRelatedWork W2355818306 @default.
- W3149920308 hasRelatedWork W2566922736 @default.
- W3149920308 hasRelatedWork W3106390345 @default.
- W3149920308 hasRelatedWork W3106890812 @default.
- W3149920308 hasRelatedWork W2253322610 @default.