Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949207039> ?p ?o ?g. }
- W2949207039 abstract "In many sequential decision-making problems we may want to manage risk by minimizing some measure of variability in costs in addition to minimizing a standard criterion. Conditional value-at-risk (CVaR) is a relatively new risk measure that addresses some of the shortcomings of the well-known variance-related risk measures, and because of its computational efficiencies has gained popularity in finance and operations research. In this paper, we consider the mean-CVaR optimization problem in MDPs. We first derive a formula for computing the gradient of this risk-sensitive objective function. We then devise policy gradient and actor-critic algorithms that each uses a specific method to estimate this gradient and updates the policy parameters in the descent direction. We establish the convergence of our algorithms to locally risk-sensitive optimal policies. Finally, we demonstrate the usefulness of our algorithms in an optimal stopping problem." @default.
- W2949207039 created "2019-06-27" @default.
- W2949207039 creator A5013843778 @default.
- W2949207039 creator A5039948454 @default.
- W2949207039 date "2014-06-12" @default.
- W2949207039 modified "2023-09-27" @default.
- W2949207039 title "Algorithms for CVaR Optimization in MDPs" @default.
- W2949207039 cites W1963835453 @default.
- W2949207039 cites W1997933673 @default.
- W2949207039 cites W2007181101 @default.
- W2949207039 cites W2019291268 @default.
- W2949207039 cites W2021270935 @default.
- W2949207039 cites W2057510529 @default.
- W2949207039 cites W2070570138 @default.
- W2949207039 cites W2073314543 @default.
- W2949207039 cites W2102288976 @default.
- W2949207039 cites W2114537044 @default.
- W2949207039 cites W2124289529 @default.
- W2949207039 cites W2128347943 @default.
- W2949207039 cites W2128723253 @default.
- W2949207039 cites W2141203641 @default.
- W2949207039 cites W2153874061 @default.
- W2949207039 cites W2161270100 @default.
- W2949207039 cites W2313791856 @default.
- W2949207039 cites W2531891978 @default.
- W2949207039 cites W2798766386 @default.
- W2949207039 cites W2949963197 @default.
- W2949207039 cites W2950270546 @default.
- W2949207039 cites W594357522 @default.
- W2949207039 cites W2624930298 @default.
- W2949207039 hasPublicationYear "2014" @default.
- W2949207039 type Work @default.
- W2949207039 sameAs 2949207039 @default.
- W2949207039 citedByCount "18" @default.
- W2949207039 countsByYear W29492070392014 @default.
- W2949207039 countsByYear W29492070392015 @default.
- W2949207039 countsByYear W29492070392016 @default.
- W2949207039 countsByYear W29492070392017 @default.
- W2949207039 countsByYear W29492070392018 @default.
- W2949207039 countsByYear W29492070392019 @default.
- W2949207039 countsByYear W29492070392020 @default.
- W2949207039 countsByYear W29492070392021 @default.
- W2949207039 crossrefType "posted-content" @default.
- W2949207039 hasAuthorship W2949207039A5013843778 @default.
- W2949207039 hasAuthorship W2949207039A5039948454 @default.
- W2949207039 hasConcept C10138342 @default.
- W2949207039 hasConcept C121955636 @default.
- W2949207039 hasConcept C124101348 @default.
- W2949207039 hasConcept C126255220 @default.
- W2949207039 hasConcept C137836250 @default.
- W2949207039 hasConcept C153258448 @default.
- W2949207039 hasConcept C154945302 @default.
- W2949207039 hasConcept C162324750 @default.
- W2949207039 hasConcept C167548438 @default.
- W2949207039 hasConcept C196083921 @default.
- W2949207039 hasConcept C2777303404 @default.
- W2949207039 hasConcept C2779922397 @default.
- W2949207039 hasConcept C2780009758 @default.
- W2949207039 hasConcept C2780821815 @default.
- W2949207039 hasConcept C2781472820 @default.
- W2949207039 hasConcept C32896092 @default.
- W2949207039 hasConcept C33923547 @default.
- W2949207039 hasConcept C41008148 @default.
- W2949207039 hasConcept C50522688 @default.
- W2949207039 hasConcept C50644808 @default.
- W2949207039 hasConcept C5496284 @default.
- W2949207039 hasConceptScore W2949207039C10138342 @default.
- W2949207039 hasConceptScore W2949207039C121955636 @default.
- W2949207039 hasConceptScore W2949207039C124101348 @default.
- W2949207039 hasConceptScore W2949207039C126255220 @default.
- W2949207039 hasConceptScore W2949207039C137836250 @default.
- W2949207039 hasConceptScore W2949207039C153258448 @default.
- W2949207039 hasConceptScore W2949207039C154945302 @default.
- W2949207039 hasConceptScore W2949207039C162324750 @default.
- W2949207039 hasConceptScore W2949207039C167548438 @default.
- W2949207039 hasConceptScore W2949207039C196083921 @default.
- W2949207039 hasConceptScore W2949207039C2777303404 @default.
- W2949207039 hasConceptScore W2949207039C2779922397 @default.
- W2949207039 hasConceptScore W2949207039C2780009758 @default.
- W2949207039 hasConceptScore W2949207039C2780821815 @default.
- W2949207039 hasConceptScore W2949207039C2781472820 @default.
- W2949207039 hasConceptScore W2949207039C32896092 @default.
- W2949207039 hasConceptScore W2949207039C33923547 @default.
- W2949207039 hasConceptScore W2949207039C41008148 @default.
- W2949207039 hasConceptScore W2949207039C50522688 @default.
- W2949207039 hasConceptScore W2949207039C50644808 @default.
- W2949207039 hasConceptScore W2949207039C5496284 @default.
- W2949207039 hasLocation W29492070391 @default.
- W2949207039 hasOpenAccess W2949207039 @default.
- W2949207039 hasPrimaryLocation W29492070391 @default.
- W2949207039 hasRelatedWork W1647779468 @default.
- W2949207039 hasRelatedWork W1975849488 @default.
- W2949207039 hasRelatedWork W2019291268 @default.
- W2949207039 hasRelatedWork W2027106436 @default.
- W2949207039 hasRelatedWork W2088413745 @default.
- W2949207039 hasRelatedWork W2119717200 @default.
- W2949207039 hasRelatedWork W2135857055 @default.
- W2949207039 hasRelatedWork W2141203641 @default.
- W2949207039 hasRelatedWork W2159223630 @default.
- W2949207039 hasRelatedWork W2162849300 @default.