Matches in SemOpenAlex for { <https://semopenalex.org/work/W4301403225> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4301403225 abstract "This paper tackles a multi-agent bandit setting where $M$ agents cooperate together to solve the same instance of a $K$-armed stochastic bandit problem. The agents are textit{heterogeneous}: each agent has limited access to a local subset of arms and the agents are asynchronous with different gaps between decision-making rounds. The goal for each agent is to find its optimal local arm, and agents can cooperate by sharing their observations with others. While cooperation between agents improves the performance of learning, it comes with an additional complexity of communication between agents. For this heterogeneous multi-agent setting, we propose two learning algorithms, ucbo and AAE. We prove that both algorithms achieve order-optimal regret, which is $Oleft(sum_{i:tilde{Delta}_i>0} log T/tilde{Delta}_iright)$, where $tilde{Delta}_i$ is the minimum suboptimality gap between the reward mean of arm $i$ and any local optimal arm. In addition, a careful selection of the valuable information for cooperation, AAE achieves a low communication complexity of $O(log T)$. Last, numerical experiments verify the efficiency of both algorithms." @default.
- W4301403225 created "2022-10-05" @default.
- W4301403225 creator A5036683370 @default.
- W4301403225 creator A5039714087 @default.
- W4301403225 creator A5046146251 @default.
- W4301403225 creator A5069352060 @default.
- W4301403225 creator A5084978931 @default.
- W4301403225 date "2022-01-23" @default.
- W4301403225 modified "2023-10-16" @default.
- W4301403225 title "Distributed Bandits with Heterogeneous Agents" @default.
- W4301403225 doi "https://doi.org/10.48550/arxiv.2201.09353" @default.
- W4301403225 hasPublicationYear "2022" @default.
- W4301403225 type Work @default.
- W4301403225 citedByCount "0" @default.
- W4301403225 crossrefType "posted-content" @default.
- W4301403225 hasAuthorship W4301403225A5036683370 @default.
- W4301403225 hasAuthorship W4301403225A5039714087 @default.
- W4301403225 hasAuthorship W4301403225A5046146251 @default.
- W4301403225 hasAuthorship W4301403225A5069352060 @default.
- W4301403225 hasAuthorship W4301403225A5084978931 @default.
- W4301403225 hasBestOaLocation W43014032251 @default.
- W4301403225 hasConcept C10138342 @default.
- W4301403225 hasConcept C114614502 @default.
- W4301403225 hasConcept C119857082 @default.
- W4301403225 hasConcept C126255220 @default.
- W4301403225 hasConcept C151319957 @default.
- W4301403225 hasConcept C162324750 @default.
- W4301403225 hasConcept C182306322 @default.
- W4301403225 hasConcept C31258907 @default.
- W4301403225 hasConcept C33923547 @default.
- W4301403225 hasConcept C36686422 @default.
- W4301403225 hasConcept C41008148 @default.
- W4301403225 hasConcept C50817715 @default.
- W4301403225 hasConceptScore W4301403225C10138342 @default.
- W4301403225 hasConceptScore W4301403225C114614502 @default.
- W4301403225 hasConceptScore W4301403225C119857082 @default.
- W4301403225 hasConceptScore W4301403225C126255220 @default.
- W4301403225 hasConceptScore W4301403225C151319957 @default.
- W4301403225 hasConceptScore W4301403225C162324750 @default.
- W4301403225 hasConceptScore W4301403225C182306322 @default.
- W4301403225 hasConceptScore W4301403225C31258907 @default.
- W4301403225 hasConceptScore W4301403225C33923547 @default.
- W4301403225 hasConceptScore W4301403225C36686422 @default.
- W4301403225 hasConceptScore W4301403225C41008148 @default.
- W4301403225 hasConceptScore W4301403225C50817715 @default.
- W4301403225 hasLocation W43014032251 @default.
- W4301403225 hasOpenAccess W4301403225 @default.
- W4301403225 hasPrimaryLocation W43014032251 @default.
- W4301403225 hasRelatedWork W1965638344 @default.
- W4301403225 hasRelatedWork W1978042415 @default.
- W4301403225 hasRelatedWork W1979843330 @default.
- W4301403225 hasRelatedWork W2021838450 @default.
- W4301403225 hasRelatedWork W2147711412 @default.
- W4301403225 hasRelatedWork W2367372208 @default.
- W4301403225 hasRelatedWork W2741527955 @default.
- W4301403225 hasRelatedWork W2964072617 @default.
- W4301403225 hasRelatedWork W3100791781 @default.
- W4301403225 hasRelatedWork W3203472452 @default.
- W4301403225 isParatext "false" @default.
- W4301403225 isRetracted "false" @default.
- W4301403225 workType "article" @default.