FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999710481> ?p ?o ?g. }

• W2999710481 abstract "We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments." @default.
• W2999710481 created "2020-01-23" @default.
• W2999710481 creator A5009722403 @default.
• W2999710481 creator A5010734725 @default.
• W2999710481 creator A5037667167 @default.
• W2999710481 creator A5049708660 @default.
• W2999710481 creator A5074675323 @default.
• W2999710481 creator A5080191195 @default.
• W2999710481 date "2020-01-15" @default.
• W2999710481 modified "2023-10-03" @default.
• W2999710481 title "Lipschitz Lifelong Reinforcement Learning" @default.
• W2999710481 cites W1505937442 @default.
• W2999710481 cites W1526654727 @default.
• W2999710481 cites W1582256513 @default.
• W2999710481 cites W158722652 @default.
• W2999710481 cites W2004030284 @default.
• W2999710481 cites W2046859786 @default.
• W2999710481 cites W2096195880 @default.
• W2999710481 cites W2097381042 @default.
• W2999710481 cites W2100755824 @default.
• W2999710481 cites W2119567691 @default.
• W2999710481 cites W2120501001 @default.
• W2999710481 cites W2121863487 @default.
• W2999710481 cites W2123447947 @default.
• W2999710481 cites W2133458291 @default.
• W2999710481 cites W2141559023 @default.
• W2999710481 cites W2167619573 @default.
• W2999710481 cites W2169743339 @default.
• W2999710481 cites W2293141270 @default.
• W2999710481 cites W2341171179 @default.
• W2999710481 cites W24272225 @default.
• W2999710481 cites W2464736835 @default.
• W2999710481 cites W2550524711 @default.
• W2999710481 cites W2568646110 @default.
• W2999710481 cites W2887671224 @default.
• W2999710481 cites W2952448454 @default.
• W2999710481 cites W2963395712 @default.
• W2999710481 cites W2963582321 @default.
• W2999710481 hasPublicationYear "2020" @default.
• W2999710481 type Work @default.
• W2999710481 sameAs 2999710481 @default.
• W2999710481 citedByCount "4" @default.
• W2999710481 countsByYear W29997104812020 @default.
• W2999710481 countsByYear W29997104812021 @default.
• W2999710481 crossrefType "posted-content" @default.
• W2999710481 hasAuthorship W2999710481A5009722403 @default.
• W2999710481 hasAuthorship W2999710481A5010734725 @default.
• W2999710481 hasAuthorship W2999710481A5037667167 @default.
• W2999710481 hasAuthorship W2999710481A5049708660 @default.
• W2999710481 hasAuthorship W2999710481A5074675323 @default.
• W2999710481 hasAuthorship W2999710481A5080191195 @default.
• W2999710481 hasConcept C105795698 @default.
• W2999710481 hasConcept C106189395 @default.
• W2999710481 hasConcept C108771440 @default.
• W2999710481 hasConcept C111919701 @default.
• W2999710481 hasConcept C119857082 @default.
• W2999710481 hasConcept C126255220 @default.
• W2999710481 hasConcept C134306372 @default.
• W2999710481 hasConcept C14646407 @default.
• W2999710481 hasConcept C150899416 @default.
• W2999710481 hasConcept C154945302 @default.
• W2999710481 hasConcept C15744967 @default.
• W2999710481 hasConcept C159886148 @default.
• W2999710481 hasConcept C162324750 @default.
• W2999710481 hasConcept C176217482 @default.
• W2999710481 hasConcept C19417346 @default.
• W2999710481 hasConcept C21547014 @default.
• W2999710481 hasConcept C22324862 @default.
• W2999710481 hasConcept C2776291640 @default.
• W2999710481 hasConcept C2777303404 @default.
• W2999710481 hasConcept C2778572836 @default.
• W2999710481 hasConcept C33923547 @default.
• W2999710481 hasConcept C41008148 @default.
• W2999710481 hasConcept C50522688 @default.
• W2999710481 hasConcept C97541855 @default.
• W2999710481 hasConcept C98763669 @default.
• W2999710481 hasConceptScore W2999710481C105795698 @default.
• W2999710481 hasConceptScore W2999710481C106189395 @default.
• W2999710481 hasConceptScore W2999710481C108771440 @default.
• W2999710481 hasConceptScore W2999710481C111919701 @default.
• W2999710481 hasConceptScore W2999710481C119857082 @default.
• W2999710481 hasConceptScore W2999710481C126255220 @default.
• W2999710481 hasConceptScore W2999710481C134306372 @default.
• W2999710481 hasConceptScore W2999710481C14646407 @default.
• W2999710481 hasConceptScore W2999710481C150899416 @default.
• W2999710481 hasConceptScore W2999710481C154945302 @default.
• W2999710481 hasConceptScore W2999710481C15744967 @default.
• W2999710481 hasConceptScore W2999710481C159886148 @default.
• W2999710481 hasConceptScore W2999710481C162324750 @default.
• W2999710481 hasConceptScore W2999710481C176217482 @default.
• W2999710481 hasConceptScore W2999710481C19417346 @default.
• W2999710481 hasConceptScore W2999710481C21547014 @default.
• W2999710481 hasConceptScore W2999710481C22324862 @default.
• W2999710481 hasConceptScore W2999710481C2776291640 @default.
• W2999710481 hasConceptScore W2999710481C2777303404 @default.
• W2999710481 hasConceptScore W2999710481C2778572836 @default.
• W2999710481 hasConceptScore W2999710481C33923547 @default.
• W2999710481 hasConceptScore W2999710481C41008148 @default.
• W2999710481 hasConceptScore W2999710481C50522688 @default.
• W2999710481 hasConceptScore W2999710481C97541855 @default.

• next