Matches in SemOpenAlex for { <https://semopenalex.org/work/W3172003993> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3172003993 endingPage "191" @default.
- W3172003993 startingPage "166" @default.
- W3172003993 abstract "In stochastic control applications, typically only an ideal model (controlled transition kernel) is assumed and the control design is based on the given model, raising the problem of performance loss due to the mismatch between the assumed model and the actual model. In some further setups, an exact model may be known, but this model may entail computationally challenging optimality analysis leading to the solution of some approximate model being implemented. With such a motivation, we study continuity properties of discrete-time stochastic control problems with respect to system models and robustness of optimal control policies designed for incorrect models applied to the true system. We study both fully observed and partially observed setups under an infinite horizon discounted expected cost criterion. We show that continuity can be established under total variation convergence of the transition kernels under mild assumptions and with further restrictions on the dynamics and observation model under weak and setwise convergence of the transition kernels. Using these, we establish convergence results and error bounds due to mismatch that occurs by the application of a control policy which is designed for an incorrectly estimated system model to the actual system, thus establishing results on robustness. These entail implications on empirical learning in (data-driven) stochastic control since often system models are learned through empirical training data where typically the weak convergence criterion applies but stronger convergence criteria do not. We finally view and establish approximation as a particular instance of robustness." @default.
- W3172003993 created "2021-06-22" @default.
- W3172003993 creator A5005401257 @default.
- W3172003993 creator A5039054529 @default.
- W3172003993 date "2021-01-01" @default.
- W3172003993 modified "2023-09-29" @default.
- W3172003993 title "Robustness to Approximations and Model Learning in MDPs and POMDPs" @default.
- W3172003993 cites W1855391364 @default.
- W3172003993 cites W1964143231 @default.
- W3172003993 cites W2004276046 @default.
- W3172003993 cites W2010654234 @default.
- W3172003993 cites W2087686387 @default.
- W3172003993 cites W2096035449 @default.
- W3172003993 cites W2113151258 @default.
- W3172003993 cites W2117843344 @default.
- W3172003993 cites W2144018496 @default.
- W3172003993 cites W2911474331 @default.
- W3172003993 cites W2963272571 @default.
- W3172003993 cites W2963292203 @default.
- W3172003993 cites W2963619045 @default.
- W3172003993 cites W2964034900 @default.
- W3172003993 cites W2974631764 @default.
- W3172003993 cites W3020371095 @default.
- W3172003993 cites W3033953991 @default.
- W3172003993 cites W3123274248 @default.
- W3172003993 cites W4210736171 @default.
- W3172003993 doi "https://doi.org/10.1007/978-3-030-76928-4_9" @default.
- W3172003993 hasPublicationYear "2021" @default.
- W3172003993 type Work @default.
- W3172003993 sameAs 3172003993 @default.
- W3172003993 citedByCount "0" @default.
- W3172003993 crossrefType "book-chapter" @default.
- W3172003993 hasAuthorship W3172003993A5005401257 @default.
- W3172003993 hasAuthorship W3172003993A5039054529 @default.
- W3172003993 hasBestOaLocation W31720039932 @default.
- W3172003993 hasConcept C104317684 @default.
- W3172003993 hasConcept C126255220 @default.
- W3172003993 hasConcept C162324750 @default.
- W3172003993 hasConcept C185592680 @default.
- W3172003993 hasConcept C26517878 @default.
- W3172003993 hasConcept C2777303404 @default.
- W3172003993 hasConcept C33923547 @default.
- W3172003993 hasConcept C38652104 @default.
- W3172003993 hasConcept C41008148 @default.
- W3172003993 hasConcept C50522688 @default.
- W3172003993 hasConcept C55479107 @default.
- W3172003993 hasConcept C55493867 @default.
- W3172003993 hasConcept C63479239 @default.
- W3172003993 hasConcept C91575142 @default.
- W3172003993 hasConceptScore W3172003993C104317684 @default.
- W3172003993 hasConceptScore W3172003993C126255220 @default.
- W3172003993 hasConceptScore W3172003993C162324750 @default.
- W3172003993 hasConceptScore W3172003993C185592680 @default.
- W3172003993 hasConceptScore W3172003993C26517878 @default.
- W3172003993 hasConceptScore W3172003993C2777303404 @default.
- W3172003993 hasConceptScore W3172003993C33923547 @default.
- W3172003993 hasConceptScore W3172003993C38652104 @default.
- W3172003993 hasConceptScore W3172003993C41008148 @default.
- W3172003993 hasConceptScore W3172003993C50522688 @default.
- W3172003993 hasConceptScore W3172003993C55479107 @default.
- W3172003993 hasConceptScore W3172003993C55493867 @default.
- W3172003993 hasConceptScore W3172003993C63479239 @default.
- W3172003993 hasConceptScore W3172003993C91575142 @default.
- W3172003993 hasLocation W31720039931 @default.
- W3172003993 hasLocation W31720039932 @default.
- W3172003993 hasOpenAccess W3172003993 @default.
- W3172003993 hasPrimaryLocation W31720039931 @default.
- W3172003993 hasRelatedWork W10227384 @default.
- W3172003993 hasRelatedWork W10507171 @default.
- W3172003993 hasRelatedWork W12390452 @default.
- W3172003993 hasRelatedWork W282544 @default.
- W3172003993 hasRelatedWork W3276279 @default.
- W3172003993 hasRelatedWork W3451101 @default.
- W3172003993 hasRelatedWork W4776762 @default.
- W3172003993 hasRelatedWork W4799626 @default.
- W3172003993 hasRelatedWork W4964836 @default.
- W3172003993 hasRelatedWork W7604782 @default.
- W3172003993 isParatext "false" @default.
- W3172003993 isRetracted "false" @default.
- W3172003993 magId "3172003993" @default.
- W3172003993 workType "book-chapter" @default.