Matches in SemOpenAlex for { <https://semopenalex.org/work/W3125709008> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3125709008 abstract "We introduce a novel framework to account for sensitivity to rewards uncertainty in sequential decision-making problems. While risk-sensitive formulations for Markov decision processes studied so far focus on the distribution of the cumulative reward as a whole, we aim at learning policies sensitive to the uncertain/stochastic nature of the rewards, which has the advantage of being conceptually more meaningful in some cases. To this end, we present a new decomposition of the randomness contained in the cumulative reward based on the Doob decomposition of a stochastic process, and introduce a new conceptual tool - the textit{chaotic variation} - which can rigorously be interpreted as the risk measure of the martingale component associated to the cumulative reward process. We innovate on the reinforcement learning side by incorporating this new risk-sensitive approach into model-free algorithms, both policy gradient and value function based, and illustrate its relevance on grid world and portfolio optimization problems." @default.
- W3125709008 created "2021-02-01" @default.
- W3125709008 creator A5019908493 @default.
- W3125709008 creator A5046489226 @default.
- W3125709008 creator A5057963205 @default.
- W3125709008 creator A5081450666 @default.
- W3125709008 date "2020-01-01" @default.
- W3125709008 modified "2023-09-27" @default.
- W3125709008 title "Risk-Sensitive Reinforcement Learning: a Martingale Approach to Reward Uncertainty" @default.
- W3125709008 hasPublicationYear "2020" @default.
- W3125709008 type Work @default.
- W3125709008 sameAs 3125709008 @default.
- W3125709008 citedByCount "0" @default.
- W3125709008 crossrefType "posted-content" @default.
- W3125709008 hasAuthorship W3125709008A5019908493 @default.
- W3125709008 hasAuthorship W3125709008A5046489226 @default.
- W3125709008 hasAuthorship W3125709008A5057963205 @default.
- W3125709008 hasAuthorship W3125709008A5081450666 @default.
- W3125709008 hasConcept C105795698 @default.
- W3125709008 hasConcept C106159729 @default.
- W3125709008 hasConcept C106189395 @default.
- W3125709008 hasConcept C125112378 @default.
- W3125709008 hasConcept C126255220 @default.
- W3125709008 hasConcept C144237770 @default.
- W3125709008 hasConcept C149782125 @default.
- W3125709008 hasConcept C154945302 @default.
- W3125709008 hasConcept C159886148 @default.
- W3125709008 hasConcept C162324750 @default.
- W3125709008 hasConcept C205706631 @default.
- W3125709008 hasConcept C2779449553 @default.
- W3125709008 hasConcept C2780821815 @default.
- W3125709008 hasConcept C28826006 @default.
- W3125709008 hasConcept C33923547 @default.
- W3125709008 hasConcept C41008148 @default.
- W3125709008 hasConcept C48406656 @default.
- W3125709008 hasConcept C97541855 @default.
- W3125709008 hasConceptScore W3125709008C105795698 @default.
- W3125709008 hasConceptScore W3125709008C106159729 @default.
- W3125709008 hasConceptScore W3125709008C106189395 @default.
- W3125709008 hasConceptScore W3125709008C125112378 @default.
- W3125709008 hasConceptScore W3125709008C126255220 @default.
- W3125709008 hasConceptScore W3125709008C144237770 @default.
- W3125709008 hasConceptScore W3125709008C149782125 @default.
- W3125709008 hasConceptScore W3125709008C154945302 @default.
- W3125709008 hasConceptScore W3125709008C159886148 @default.
- W3125709008 hasConceptScore W3125709008C162324750 @default.
- W3125709008 hasConceptScore W3125709008C205706631 @default.
- W3125709008 hasConceptScore W3125709008C2779449553 @default.
- W3125709008 hasConceptScore W3125709008C2780821815 @default.
- W3125709008 hasConceptScore W3125709008C28826006 @default.
- W3125709008 hasConceptScore W3125709008C33923547 @default.
- W3125709008 hasConceptScore W3125709008C41008148 @default.
- W3125709008 hasConceptScore W3125709008C48406656 @default.
- W3125709008 hasConceptScore W3125709008C97541855 @default.
- W3125709008 hasLocation W31257090081 @default.
- W3125709008 hasOpenAccess W3125709008 @default.
- W3125709008 hasPrimaryLocation W31257090081 @default.
- W3125709008 hasRelatedWork W1496855202 @default.
- W3125709008 hasRelatedWork W185316597 @default.
- W3125709008 hasRelatedWork W1981587768 @default.
- W3125709008 hasRelatedWork W2058066080 @default.
- W3125709008 hasRelatedWork W2103042852 @default.
- W3125709008 hasRelatedWork W2141203641 @default.
- W3125709008 hasRelatedWork W2187555640 @default.
- W3125709008 hasRelatedWork W2398644227 @default.
- W3125709008 hasRelatedWork W2739473244 @default.
- W3125709008 hasRelatedWork W2892360866 @default.
- W3125709008 hasRelatedWork W2952186752 @default.
- W3125709008 hasRelatedWork W2965092272 @default.
- W3125709008 hasRelatedWork W2969329284 @default.
- W3125709008 hasRelatedWork W3036684478 @default.
- W3125709008 hasRelatedWork W3105333898 @default.
- W3125709008 hasRelatedWork W3175189009 @default.
- W3125709008 hasRelatedWork W3189815242 @default.
- W3125709008 hasRelatedWork W3194439889 @default.
- W3125709008 hasRelatedWork W762189110 @default.
- W3125709008 hasRelatedWork W9932698 @default.
- W3125709008 isParatext "false" @default.
- W3125709008 isRetracted "false" @default.
- W3125709008 magId "3125709008" @default.
- W3125709008 workType "article" @default.