Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385020057> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4385020057 abstract "We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our work departs from the typical approach of treating advice as coming from black-box sources by instead considering a setting where additional information about how the advice is generated is available. We prove a first-of-its-kind consistency and robustness tradeoff given Q-value advice under a general MDP model that includes both continuous and discrete state/action spaces. Our results highlight that utilizing Q-value advice enables dynamic pursuit of the better of machine-learned advice and a robust baseline, thus result in near-optimal performance guarantees, which provably improves what can be obtained solely with black-box advice." @default.
- W4385020057 created "2023-07-22" @default.
- W4385020057 creator A5000834239 @default.
- W4385020057 creator A5005758616 @default.
- W4385020057 creator A5006928264 @default.
- W4385020057 creator A5062565732 @default.
- W4385020057 date "2023-07-19" @default.
- W4385020057 modified "2023-10-17" @default.
- W4385020057 title "Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions" @default.
- W4385020057 doi "https://doi.org/10.48550/arxiv.2307.10524" @default.
- W4385020057 hasPublicationYear "2023" @default.
- W4385020057 type Work @default.
- W4385020057 citedByCount "0" @default.
- W4385020057 crossrefType "posted-content" @default.
- W4385020057 hasAuthorship W4385020057A5000834239 @default.
- W4385020057 hasAuthorship W4385020057A5005758616 @default.
- W4385020057 hasAuthorship W4385020057A5006928264 @default.
- W4385020057 hasAuthorship W4385020057A5062565732 @default.
- W4385020057 hasBestOaLocation W43850200571 @default.
- W4385020057 hasConcept C104317684 @default.
- W4385020057 hasConcept C105795698 @default.
- W4385020057 hasConcept C106189395 @default.
- W4385020057 hasConcept C11413529 @default.
- W4385020057 hasConcept C119857082 @default.
- W4385020057 hasConcept C126255220 @default.
- W4385020057 hasConcept C151730666 @default.
- W4385020057 hasConcept C154945302 @default.
- W4385020057 hasConcept C159886148 @default.
- W4385020057 hasConcept C185592680 @default.
- W4385020057 hasConcept C199360897 @default.
- W4385020057 hasConcept C2776436953 @default.
- W4385020057 hasConcept C2779343474 @default.
- W4385020057 hasConcept C2779955035 @default.
- W4385020057 hasConcept C33923547 @default.
- W4385020057 hasConcept C41008148 @default.
- W4385020057 hasConcept C55493867 @default.
- W4385020057 hasConcept C63479239 @default.
- W4385020057 hasConcept C86803240 @default.
- W4385020057 hasConcept C94966114 @default.
- W4385020057 hasConceptScore W4385020057C104317684 @default.
- W4385020057 hasConceptScore W4385020057C105795698 @default.
- W4385020057 hasConceptScore W4385020057C106189395 @default.
- W4385020057 hasConceptScore W4385020057C11413529 @default.
- W4385020057 hasConceptScore W4385020057C119857082 @default.
- W4385020057 hasConceptScore W4385020057C126255220 @default.
- W4385020057 hasConceptScore W4385020057C151730666 @default.
- W4385020057 hasConceptScore W4385020057C154945302 @default.
- W4385020057 hasConceptScore W4385020057C159886148 @default.
- W4385020057 hasConceptScore W4385020057C185592680 @default.
- W4385020057 hasConceptScore W4385020057C199360897 @default.
- W4385020057 hasConceptScore W4385020057C2776436953 @default.
- W4385020057 hasConceptScore W4385020057C2779343474 @default.
- W4385020057 hasConceptScore W4385020057C2779955035 @default.
- W4385020057 hasConceptScore W4385020057C33923547 @default.
- W4385020057 hasConceptScore W4385020057C41008148 @default.
- W4385020057 hasConceptScore W4385020057C55493867 @default.
- W4385020057 hasConceptScore W4385020057C63479239 @default.
- W4385020057 hasConceptScore W4385020057C86803240 @default.
- W4385020057 hasConceptScore W4385020057C94966114 @default.
- W4385020057 hasLocation W43850200571 @default.
- W4385020057 hasOpenAccess W4385020057 @default.
- W4385020057 hasPrimaryLocation W43850200571 @default.
- W4385020057 hasRelatedWork W1562091114 @default.
- W4385020057 hasRelatedWork W1994682696 @default.
- W4385020057 hasRelatedWork W1996326480 @default.
- W4385020057 hasRelatedWork W2100249892 @default.
- W4385020057 hasRelatedWork W2156021013 @default.
- W4385020057 hasRelatedWork W2156992384 @default.
- W4385020057 hasRelatedWork W2161367706 @default.
- W4385020057 hasRelatedWork W2934856058 @default.
- W4385020057 hasRelatedWork W3013781205 @default.
- W4385020057 hasRelatedWork W3174740571 @default.
- W4385020057 isParatext "false" @default.
- W4385020057 isRetracted "false" @default.
- W4385020057 workType "article" @default.