Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287765290> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4287765290 abstract "Online recommender systems often face long delays in receiving feedback, especially when optimizing for some long-term metrics. While mitigating the effects of delays in learning is well-understood in stationary environments, the problem becomes much more challenging when the environment changes. In fact, if the timescale of the change is comparable to the delay, it is impossible to learn about the environment, since the available observations are already obsolete. However, the arising issues can be addressed if intermediate signals are available without delay, such that given those signals, the long-term behavior of the system is stationary. To model this situation, we introduce the problem of stochastic, non-stationary, delayed bandits with intermediate observations. We develop a computationally efficient algorithm based on UCRL, and prove sublinear regret guarantees for its performance. Experimental results demonstrate that our method is able to learn in non-stationary delayed environments where existing methods fail." @default.
- W4287765290 created "2022-07-26" @default.
- W4287765290 creator A5006380946 @default.
- W4287765290 creator A5041609088 @default.
- W4287765290 creator A5088066921 @default.
- W4287765290 date "2020-06-03" @default.
- W4287765290 modified "2023-09-27" @default.
- W4287765290 title "Non-Stationary Delayed Bandits with Intermediate Observations" @default.
- W4287765290 doi "https://doi.org/10.48550/arxiv.2006.02119" @default.
- W4287765290 hasPublicationYear "2020" @default.
- W4287765290 type Work @default.
- W4287765290 citedByCount "0" @default.
- W4287765290 crossrefType "posted-content" @default.
- W4287765290 hasAuthorship W4287765290A5006380946 @default.
- W4287765290 hasAuthorship W4287765290A5041609088 @default.
- W4287765290 hasAuthorship W4287765290A5088066921 @default.
- W4287765290 hasBestOaLocation W42877652901 @default.
- W4287765290 hasConcept C117160843 @default.
- W4287765290 hasConcept C119857082 @default.
- W4287765290 hasConcept C121332964 @default.
- W4287765290 hasConcept C126255220 @default.
- W4287765290 hasConcept C134306372 @default.
- W4287765290 hasConcept C136764020 @default.
- W4287765290 hasConcept C2986087404 @default.
- W4287765290 hasConcept C33923547 @default.
- W4287765290 hasConcept C41008148 @default.
- W4287765290 hasConcept C50817715 @default.
- W4287765290 hasConcept C61797465 @default.
- W4287765290 hasConcept C62520636 @default.
- W4287765290 hasConceptScore W4287765290C117160843 @default.
- W4287765290 hasConceptScore W4287765290C119857082 @default.
- W4287765290 hasConceptScore W4287765290C121332964 @default.
- W4287765290 hasConceptScore W4287765290C126255220 @default.
- W4287765290 hasConceptScore W4287765290C134306372 @default.
- W4287765290 hasConceptScore W4287765290C136764020 @default.
- W4287765290 hasConceptScore W4287765290C2986087404 @default.
- W4287765290 hasConceptScore W4287765290C33923547 @default.
- W4287765290 hasConceptScore W4287765290C41008148 @default.
- W4287765290 hasConceptScore W4287765290C50817715 @default.
- W4287765290 hasConceptScore W4287765290C61797465 @default.
- W4287765290 hasConceptScore W4287765290C62520636 @default.
- W4287765290 hasLocation W42877652901 @default.
- W4287765290 hasOpenAccess W4287765290 @default.
- W4287765290 hasPrimaryLocation W42877652901 @default.
- W4287765290 hasRelatedWork W2915808490 @default.
- W4287765290 hasRelatedWork W2951945213 @default.
- W4287765290 hasRelatedWork W2992689132 @default.
- W4287765290 hasRelatedWork W3009321257 @default.
- W4287765290 hasRelatedWork W3035596066 @default.
- W4287765290 hasRelatedWork W3164801954 @default.
- W4287765290 hasRelatedWork W3176910946 @default.
- W4287765290 hasRelatedWork W3211820441 @default.
- W4287765290 hasRelatedWork W4287905651 @default.
- W4287765290 hasRelatedWork W4287999668 @default.
- W4287765290 isParatext "false" @default.
- W4287765290 isRetracted "false" @default.
- W4287765290 workType "article" @default.