FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3187058111> ?p ?o ?g. }

• W3187058111 abstract "We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with a goal of improving their collective performance through inter-player information sharing. We design and analyze an algorithm based on the idea of model transfer, and provide gap-dependent and gap-independent upper and lower bounds that characterize the intrinsic complexity of the problem." @default.
• W3187058111 created "2021-08-02" @default.
• W3187058111 creator A5036016529 @default.
• W3187058111 creator A5066555678 @default.
• W3187058111 date "2021-07-19" @default.
• W3187058111 modified "2023-09-23" @default.
• W3187058111 title "Provably Efficient Multi-Task Reinforcement Learning with Model Transfer" @default.
• W3187058111 cites W1517383877 @default.
• W3187058111 cites W1528133536 @default.
• W3187058111 cites W1583155004 @default.
• W3187058111 cites W158722652 @default.
• W3187058111 cites W1662803991 @default.
• W3187058111 cites W1786332878 @default.
• W3187058111 cites W1850488217 @default.
• W3187058111 cites W2004030284 @default.
• W3187058111 cites W2083459869 @default.
• W3187058111 cites W2097381042 @default.
• W3187058111 cites W2110292307 @default.
• W3187058111 cites W2142502798 @default.
• W3187058111 cites W2142620093 @default.
• W3187058111 cites W2145983895 @default.
• W3187058111 cites W2214971211 @default.
• W3187058111 cites W2528846071 @default.
• W3187058111 cites W2552021908 @default.
• W3187058111 cites W2567415945 @default.
• W3187058111 cites W2911450448 @default.
• W3187058111 cites W2912139568 @default.
• W3187058111 cites W2913340405 @default.
• W3187058111 cites W2944264312 @default.
• W3187058111 cites W2945322269 @default.
• W3187058111 cites W2957144066 @default.
• W3187058111 cites W2962723383 @default.
• W3187058111 cites W2962910611 @default.
• W3187058111 cites W2963049774 @default.
• W3187058111 cites W2963190967 @default.
• W3187058111 cites W2963490519 @default.
• W3187058111 cites W2963582321 @default.
• W3187058111 cites W2963747324 @default.
• W3187058111 cites W2964054583 @default.
• W3187058111 cites W2964299116 @default.
• W3187058111 cites W2968526727 @default.
• W3187058111 cites W2979766322 @default.
• W3187058111 cites W2991046523 @default.
• W3187058111 cites W2995481444 @default.
• W3187058111 cites W3005294098 @default.
• W3187058111 cites W3009953896 @default.
• W3187058111 cites W3035219538 @default.
• W3187058111 cites W3085267010 @default.
• W3187058111 cites W3104032756 @default.
• W3187058111 cites W3128125857 @default.
• W3187058111 cites W3143815010 @default.
• W3187058111 cites W3157288807 @default.
• W3187058111 cites W3157633619 @default.
• W3187058111 cites W3169846975 @default.
• W3187058111 doi "https://doi.org/10.48550/arxiv.2107.08622" @default.
• W3187058111 hasPublicationYear "2021" @default.
• W3187058111 type Work @default.
• W3187058111 sameAs 3187058111 @default.
• W3187058111 citedByCount "1" @default.
• W3187058111 countsByYear W31870581112021 @default.
• W3187058111 crossrefType "posted-content" @default.
• W3187058111 hasAuthorship W3187058111A5036016529 @default.
• W3187058111 hasAuthorship W3187058111A5066555678 @default.
• W3187058111 hasBestOaLocation W31870581111 @default.
• W3187058111 hasConcept C105795698 @default.
• W3187058111 hasConcept C106189395 @default.
• W3187058111 hasConcept C119857082 @default.
• W3187058111 hasConcept C150899416 @default.
• W3187058111 hasConcept C154945302 @default.
• W3187058111 hasConcept C159886148 @default.
• W3187058111 hasConcept C162324750 @default.
• W3187058111 hasConcept C187736073 @default.
• W3187058111 hasConcept C2778445095 @default.
• W3187058111 hasConcept C2780451532 @default.
• W3187058111 hasConcept C33923547 @default.
• W3187058111 hasConcept C41008148 @default.
• W3187058111 hasConcept C97541855 @default.
• W3187058111 hasConcept C98763669 @default.
• W3187058111 hasConceptScore W3187058111C105795698 @default.
• W3187058111 hasConceptScore W3187058111C106189395 @default.
• W3187058111 hasConceptScore W3187058111C119857082 @default.
• W3187058111 hasConceptScore W3187058111C150899416 @default.
• W3187058111 hasConceptScore W3187058111C154945302 @default.
• W3187058111 hasConceptScore W3187058111C159886148 @default.
• W3187058111 hasConceptScore W3187058111C162324750 @default.
• W3187058111 hasConceptScore W3187058111C187736073 @default.
• W3187058111 hasConceptScore W3187058111C2778445095 @default.
• W3187058111 hasConceptScore W3187058111C2780451532 @default.
• W3187058111 hasConceptScore W3187058111C33923547 @default.
• W3187058111 hasConceptScore W3187058111C41008148 @default.
• W3187058111 hasConceptScore W3187058111C97541855 @default.
• W3187058111 hasConceptScore W3187058111C98763669 @default.
• W3187058111 hasLocation W31870581111 @default.
• W3187058111 hasOpenAccess W3187058111 @default.
• W3187058111 hasPrimaryLocation W31870581111 @default.
• W3187058111 hasRelatedWork W1517383877 @default.
• W3187058111 hasRelatedWork W2124144580 @default.
• W3187058111 hasRelatedWork W2952448454 @default.
• W3187058111 hasRelatedWork W2970162659 @default.
• W3187058111 hasRelatedWork W2996320348 @default.

• next