Matches in SemOpenAlex for { <https://semopenalex.org/work/W3019905104> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3019905104 endingPage "1320" @default.
- W3019905104 startingPage "1314" @default.
- W3019905104 abstract "We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point problem. The outer loop performs $Q-$ learning to compute an optimal risk-aware policy. Several widely investigated risk measures (e.g., conditional value-at-risk, optimized certainty equivalent, and absolute semideviation) are covered by our algorithm. Almost sure convergence and the convergence rate of the algorithm are established. For an error tolerance $epsilon >0$ for optimal $Q$ -value estimation gap and learning rate $kin (1/2,,1]$ , the overall convergence rate of our algorithm is $Omega ((ln (1/delta epsilon)/epsilon ^{2})^{1/k}+(ln (1/epsilon))^{1/(1-k)})$ with probability at least $1-delta$ ." @default.
- W3019905104 created "2020-05-01" @default.
- W3019905104 creator A5019863108 @default.
- W3019905104 creator A5070019149 @default.
- W3019905104 date "2021-03-01" @default.
- W3019905104 modified "2023-10-08" @default.
- W3019905104 title "Stochastic Approximation for Risk-Aware Markov Decision Processes" @default.
- W3019905104 cites W1557517019 @default.
- W3019905104 cites W1587828677 @default.
- W3019905104 cites W1775297201 @default.
- W3019905104 cites W1976406849 @default.
- W3019905104 cites W1992208280 @default.
- W3019905104 cites W2001009060 @default.
- W3019905104 cites W2027106436 @default.
- W3019905104 cites W2045843884 @default.
- W3019905104 cites W2048052425 @default.
- W3019905104 cites W2049968883 @default.
- W3019905104 cites W2054321814 @default.
- W3019905104 cites W2071983464 @default.
- W3019905104 cites W2076337359 @default.
- W3019905104 cites W2083231020 @default.
- W3019905104 cites W2107431923 @default.
- W3019905104 cites W2109122936 @default.
- W3019905104 cites W2109427113 @default.
- W3019905104 cites W2128347943 @default.
- W3019905104 cites W2134802631 @default.
- W3019905104 cites W2139914196 @default.
- W3019905104 cites W2142865798 @default.
- W3019905104 cites W2155581291 @default.
- W3019905104 cites W2160769068 @default.
- W3019905104 cites W2165131254 @default.
- W3019905104 cites W2462780152 @default.
- W3019905104 cites W3125893104 @default.
- W3019905104 cites W4213065535 @default.
- W3019905104 cites W4233696721 @default.
- W3019905104 cites W4243772471 @default.
- W3019905104 cites W4249513058 @default.
- W3019905104 cites W51049863 @default.
- W3019905104 doi "https://doi.org/10.1109/tac.2020.2989702" @default.
- W3019905104 hasPublicationYear "2021" @default.
- W3019905104 type Work @default.
- W3019905104 sameAs 3019905104 @default.
- W3019905104 citedByCount "7" @default.
- W3019905104 countsByYear W30199051042019 @default.
- W3019905104 countsByYear W30199051042021 @default.
- W3019905104 countsByYear W30199051042022 @default.
- W3019905104 countsByYear W30199051042023 @default.
- W3019905104 crossrefType "journal-article" @default.
- W3019905104 hasAuthorship W3019905104A5019863108 @default.
- W3019905104 hasAuthorship W3019905104A5070019149 @default.
- W3019905104 hasBestOaLocation W30199051042 @default.
- W3019905104 hasConcept C105795698 @default.
- W3019905104 hasConcept C106189395 @default.
- W3019905104 hasConcept C119857082 @default.
- W3019905104 hasConcept C126255220 @default.
- W3019905104 hasConcept C159886148 @default.
- W3019905104 hasConcept C33923547 @default.
- W3019905104 hasConcept C41008148 @default.
- W3019905104 hasConcept C8272713 @default.
- W3019905104 hasConcept C98763669 @default.
- W3019905104 hasConceptScore W3019905104C105795698 @default.
- W3019905104 hasConceptScore W3019905104C106189395 @default.
- W3019905104 hasConceptScore W3019905104C119857082 @default.
- W3019905104 hasConceptScore W3019905104C126255220 @default.
- W3019905104 hasConceptScore W3019905104C159886148 @default.
- W3019905104 hasConceptScore W3019905104C33923547 @default.
- W3019905104 hasConceptScore W3019905104C41008148 @default.
- W3019905104 hasConceptScore W3019905104C8272713 @default.
- W3019905104 hasConceptScore W3019905104C98763669 @default.
- W3019905104 hasFunder F4320320671 @default.
- W3019905104 hasFunder F4320320751 @default.
- W3019905104 hasIssue "3" @default.
- W3019905104 hasLocation W30199051041 @default.
- W3019905104 hasLocation W30199051042 @default.
- W3019905104 hasOpenAccess W3019905104 @default.
- W3019905104 hasPrimaryLocation W30199051041 @default.
- W3019905104 hasRelatedWork W2002454365 @default.
- W3019905104 hasRelatedWork W2029959279 @default.
- W3019905104 hasRelatedWork W2114001769 @default.
- W3019905104 hasRelatedWork W2161367706 @default.
- W3019905104 hasRelatedWork W2168092340 @default.
- W3019905104 hasRelatedWork W2588381834 @default.
- W3019905104 hasRelatedWork W2913022628 @default.
- W3019905104 hasRelatedWork W3135179687 @default.
- W3019905104 hasRelatedWork W3198596521 @default.
- W3019905104 hasRelatedWork W578701343 @default.
- W3019905104 hasVolume "66" @default.
- W3019905104 isParatext "false" @default.
- W3019905104 isRetracted "false" @default.
- W3019905104 magId "3019905104" @default.
- W3019905104 workType "article" @default.