Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285679304> ?p ?o ?g. }
- W4285679304 endingPage "100165" @default.
- W4285679304 startingPage "100165" @default.
- W4285679304 abstract "This paper proposes an optimistic value iteration for steady-state mean–variance optimization in infinite-horizon discounted Markov decision processes (MDPs). The involved variance metric concerns reward variability in the long run, and future deviations are discounted to their present values. This mean–variance optimality criterion is time-inconsistent since its reward function depends on the mean, which renders traditional dynamic programming methods inapplicable. A family of policy/value iteration algorithms can be developed under a bilevel optimization algorithm framework, but there are still several problems to solve for a reinforcement learning (RL) extension. One problem is that in the value iteration, the inner optimization should achieve a near-optimal solution to ensure convergence before the outer update, which is required in every outer iteration. However, in an RL scenario, it is impractical to determine when the inner optimization should be stopped. To deal with this problem, we propose an optimistic value iteration, where the outer updates can be merged into the inner optimization with a learning rate. We prove the algorithm convergence and conduct a numerical experiment on portfolio management to validate the proposed algorithm." @default.
- W4285679304 created "2022-07-17" @default.
- W4285679304 creator A5022564470 @default.
- W4285679304 creator A5023240248 @default.
- W4285679304 creator A5027912723 @default.
- W4285679304 date "2022-09-01" @default.
- W4285679304 modified "2023-10-18" @default.
- W4285679304 title "An optimistic value iteration for mean–variance optimization in discounted Markov decision processes" @default.
- W4285679304 cites W1980079915 @default.
- W4285679304 cites W1993239624 @default.
- W4285679304 cites W2006115861 @default.
- W4285679304 cites W2015167078 @default.
- W4285679304 cites W2024928738 @default.
- W4285679304 cites W2041946752 @default.
- W4285679304 cites W2057510529 @default.
- W4285679304 cites W2067110063 @default.
- W4285679304 cites W2096369746 @default.
- W4285679304 cites W2253252141 @default.
- W4285679304 cites W2313791856 @default.
- W4285679304 cites W2519236774 @default.
- W4285679304 cites W2803934225 @default.
- W4285679304 cites W3035020089 @default.
- W4285679304 cites W3046677588 @default.
- W4285679304 cites W3047623911 @default.
- W4285679304 cites W3177161388 @default.
- W4285679304 doi "https://doi.org/10.1016/j.rico.2022.100165" @default.
- W4285679304 hasPublicationYear "2022" @default.
- W4285679304 type Work @default.
- W4285679304 citedByCount "0" @default.
- W4285679304 crossrefType "journal-article" @default.
- W4285679304 hasAuthorship W4285679304A5022564470 @default.
- W4285679304 hasAuthorship W4285679304A5023240248 @default.
- W4285679304 hasAuthorship W4285679304A5027912723 @default.
- W4285679304 hasBestOaLocation W42856793041 @default.
- W4285679304 hasConcept C10138342 @default.
- W4285679304 hasConcept C105795698 @default.
- W4285679304 hasConcept C106189395 @default.
- W4285679304 hasConcept C119857082 @default.
- W4285679304 hasConcept C121955636 @default.
- W4285679304 hasConcept C126255220 @default.
- W4285679304 hasConcept C137836250 @default.
- W4285679304 hasConcept C144133560 @default.
- W4285679304 hasConcept C14646407 @default.
- W4285679304 hasConcept C154945302 @default.
- W4285679304 hasConcept C159886148 @default.
- W4285679304 hasConcept C162324750 @default.
- W4285679304 hasConcept C176217482 @default.
- W4285679304 hasConcept C196083921 @default.
- W4285679304 hasConcept C202655437 @default.
- W4285679304 hasConcept C21547014 @default.
- W4285679304 hasConcept C2776291640 @default.
- W4285679304 hasConcept C2777303404 @default.
- W4285679304 hasConcept C2780821815 @default.
- W4285679304 hasConcept C33923547 @default.
- W4285679304 hasConcept C37404715 @default.
- W4285679304 hasConcept C41008148 @default.
- W4285679304 hasConcept C50522688 @default.
- W4285679304 hasConcept C97541855 @default.
- W4285679304 hasConcept C98763669 @default.
- W4285679304 hasConceptScore W4285679304C10138342 @default.
- W4285679304 hasConceptScore W4285679304C105795698 @default.
- W4285679304 hasConceptScore W4285679304C106189395 @default.
- W4285679304 hasConceptScore W4285679304C119857082 @default.
- W4285679304 hasConceptScore W4285679304C121955636 @default.
- W4285679304 hasConceptScore W4285679304C126255220 @default.
- W4285679304 hasConceptScore W4285679304C137836250 @default.
- W4285679304 hasConceptScore W4285679304C144133560 @default.
- W4285679304 hasConceptScore W4285679304C14646407 @default.
- W4285679304 hasConceptScore W4285679304C154945302 @default.
- W4285679304 hasConceptScore W4285679304C159886148 @default.
- W4285679304 hasConceptScore W4285679304C162324750 @default.
- W4285679304 hasConceptScore W4285679304C176217482 @default.
- W4285679304 hasConceptScore W4285679304C196083921 @default.
- W4285679304 hasConceptScore W4285679304C202655437 @default.
- W4285679304 hasConceptScore W4285679304C21547014 @default.
- W4285679304 hasConceptScore W4285679304C2776291640 @default.
- W4285679304 hasConceptScore W4285679304C2777303404 @default.
- W4285679304 hasConceptScore W4285679304C2780821815 @default.
- W4285679304 hasConceptScore W4285679304C33923547 @default.
- W4285679304 hasConceptScore W4285679304C37404715 @default.
- W4285679304 hasConceptScore W4285679304C41008148 @default.
- W4285679304 hasConceptScore W4285679304C50522688 @default.
- W4285679304 hasConceptScore W4285679304C97541855 @default.
- W4285679304 hasConceptScore W4285679304C98763669 @default.
- W4285679304 hasFunder F4320321001 @default.
- W4285679304 hasFunder F4320321160 @default.
- W4285679304 hasFunder F4320330330 @default.
- W4285679304 hasFunder F4320335787 @default.
- W4285679304 hasFunder F4320337111 @default.
- W4285679304 hasLocation W42856793041 @default.
- W4285679304 hasLocation W42856793042 @default.
- W4285679304 hasOpenAccess W4285679304 @default.
- W4285679304 hasPrimaryLocation W42856793041 @default.
- W4285679304 hasRelatedWork W1511927616 @default.
- W4285679304 hasRelatedWork W2117282672 @default.
- W4285679304 hasRelatedWork W2145363145 @default.
- W4285679304 hasRelatedWork W2156992384 @default.
- W4285679304 hasRelatedWork W2172425052 @default.