Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176022311> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3176022311 endingPage "8957" @default.
- W3176022311 startingPage "8950" @default.
- W3176022311 abstract "We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus on playing near-optimal arms. To this end, we suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some e. We then present a variant of the Thompson Sampling (TS) algorithm, called e-TS, and prove its asymptotic optimality in terms of the lenient regret. Importantly, we show that when the mean of the optimal arm is high enough, the lenient regret of e-TS is bounded by a constant. Finally, we show that e-TS can be applied to improve the performance when the agent knows a lower bound of the suboptimality gaps." @default.
- W3176022311 created "2021-07-05" @default.
- W3176022311 creator A5018784842 @default.
- W3176022311 creator A5036260775 @default.
- W3176022311 date "2020-08-10" @default.
- W3176022311 modified "2023-09-24" @default.
- W3176022311 title "Lenient Regret for Multi-Armed Bandits" @default.
- W3176022311 hasPublicationYear "2020" @default.
- W3176022311 type Work @default.
- W3176022311 sameAs 3176022311 @default.
- W3176022311 citedByCount "1" @default.
- W3176022311 countsByYear W31760223112021 @default.
- W3176022311 crossrefType "proceedings-article" @default.
- W3176022311 hasAuthorship W3176022311A5018784842 @default.
- W3176022311 hasAuthorship W3176022311A5036260775 @default.
- W3176022311 hasConcept C119857082 @default.
- W3176022311 hasConcept C121332964 @default.
- W3176022311 hasConcept C126255220 @default.
- W3176022311 hasConcept C134306372 @default.
- W3176022311 hasConcept C199360897 @default.
- W3176022311 hasConcept C2777027219 @default.
- W3176022311 hasConcept C2780791683 @default.
- W3176022311 hasConcept C33923547 @default.
- W3176022311 hasConcept C34388435 @default.
- W3176022311 hasConcept C41008148 @default.
- W3176022311 hasConcept C50817715 @default.
- W3176022311 hasConcept C62520636 @default.
- W3176022311 hasConcept C73602740 @default.
- W3176022311 hasConcept C77553402 @default.
- W3176022311 hasConceptScore W3176022311C119857082 @default.
- W3176022311 hasConceptScore W3176022311C121332964 @default.
- W3176022311 hasConceptScore W3176022311C126255220 @default.
- W3176022311 hasConceptScore W3176022311C134306372 @default.
- W3176022311 hasConceptScore W3176022311C199360897 @default.
- W3176022311 hasConceptScore W3176022311C2777027219 @default.
- W3176022311 hasConceptScore W3176022311C2780791683 @default.
- W3176022311 hasConceptScore W3176022311C33923547 @default.
- W3176022311 hasConceptScore W3176022311C34388435 @default.
- W3176022311 hasConceptScore W3176022311C41008148 @default.
- W3176022311 hasConceptScore W3176022311C50817715 @default.
- W3176022311 hasConceptScore W3176022311C62520636 @default.
- W3176022311 hasConceptScore W3176022311C73602740 @default.
- W3176022311 hasConceptScore W3176022311C77553402 @default.
- W3176022311 hasIssue "10" @default.
- W3176022311 hasLocation W31760223111 @default.
- W3176022311 hasOpenAccess W3176022311 @default.
- W3176022311 hasPrimaryLocation W31760223111 @default.
- W3176022311 hasRelatedWork W1901466015 @default.
- W3176022311 hasRelatedWork W2109690147 @default.
- W3176022311 hasRelatedWork W2223417493 @default.
- W3176022311 hasRelatedWork W246157401 @default.
- W3176022311 hasRelatedWork W2576746119 @default.
- W3176022311 hasRelatedWork W2603526483 @default.
- W3176022311 hasRelatedWork W2796393948 @default.
- W3176022311 hasRelatedWork W2914049206 @default.
- W3176022311 hasRelatedWork W2952215778 @default.
- W3176022311 hasRelatedWork W2963186828 @default.
- W3176022311 hasRelatedWork W2963870676 @default.
- W3176022311 hasRelatedWork W3008889843 @default.
- W3176022311 hasRelatedWork W3038006069 @default.
- W3176022311 hasRelatedWork W3048056964 @default.
- W3176022311 hasRelatedWork W3124285628 @default.
- W3176022311 hasRelatedWork W3124379662 @default.
- W3176022311 hasRelatedWork W3156667892 @default.
- W3176022311 hasRelatedWork W3203539123 @default.
- W3176022311 hasRelatedWork W762176534 @default.
- W3176022311 hasRelatedWork W102889024 @default.
- W3176022311 hasVolume "35" @default.
- W3176022311 isParatext "false" @default.
- W3176022311 isRetracted "false" @default.
- W3176022311 magId "3176022311" @default.
- W3176022311 workType "article" @default.