Matches in SemOpenAlex for { <https://semopenalex.org/work/W2399136500> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2399136500 abstract "Most existing reinforcement learning algorithms require many trials until they obtain optimal policies. In this study, we apply transfer learning to reinforcement learning to realize greater efficiency. We propose a new algorithm called TR-MAX, based on the R-MAX algorithm. TR-MAX transfers the transition and reward probabilities from a source task to a target task as prior knowledge. We theoretically analyze the sample complexity of TR-MAX. Moreover, we show that TR-MAX performs much better in practice than R-MAX in maze tasks." @default.
- W2399136500 created "2016-06-24" @default.
- W2399136500 creator A5015864359 @default.
- W2399136500 creator A5055103053 @default.
- W2399136500 creator A5071075962 @default.
- W2399136500 date "2014-01-01" @default.
- W2399136500 modified "2023-09-27" @default.
- W2399136500 title "Reducing Sample Complexity in Reinforcement Learning by Transferring Transition and Reward Probabilities" @default.
- W2399136500 doi "https://doi.org/10.5220/0004915606320638" @default.
- W2399136500 hasPublicationYear "2014" @default.
- W2399136500 type Work @default.
- W2399136500 sameAs 2399136500 @default.
- W2399136500 citedByCount "0" @default.
- W2399136500 crossrefType "proceedings-article" @default.
- W2399136500 hasAuthorship W2399136500A5015864359 @default.
- W2399136500 hasAuthorship W2399136500A5055103053 @default.
- W2399136500 hasAuthorship W2399136500A5071075962 @default.
- W2399136500 hasConcept C119857082 @default.
- W2399136500 hasConcept C127413603 @default.
- W2399136500 hasConcept C150899416 @default.
- W2399136500 hasConcept C154945302 @default.
- W2399136500 hasConcept C15744967 @default.
- W2399136500 hasConcept C185592680 @default.
- W2399136500 hasConcept C198531522 @default.
- W2399136500 hasConcept C201995342 @default.
- W2399136500 hasConcept C2778445095 @default.
- W2399136500 hasConcept C2780451532 @default.
- W2399136500 hasConcept C41008148 @default.
- W2399136500 hasConcept C43617362 @default.
- W2399136500 hasConcept C67203356 @default.
- W2399136500 hasConcept C77805123 @default.
- W2399136500 hasConcept C97541855 @default.
- W2399136500 hasConceptScore W2399136500C119857082 @default.
- W2399136500 hasConceptScore W2399136500C127413603 @default.
- W2399136500 hasConceptScore W2399136500C150899416 @default.
- W2399136500 hasConceptScore W2399136500C154945302 @default.
- W2399136500 hasConceptScore W2399136500C15744967 @default.
- W2399136500 hasConceptScore W2399136500C185592680 @default.
- W2399136500 hasConceptScore W2399136500C198531522 @default.
- W2399136500 hasConceptScore W2399136500C201995342 @default.
- W2399136500 hasConceptScore W2399136500C2778445095 @default.
- W2399136500 hasConceptScore W2399136500C2780451532 @default.
- W2399136500 hasConceptScore W2399136500C41008148 @default.
- W2399136500 hasConceptScore W2399136500C43617362 @default.
- W2399136500 hasConceptScore W2399136500C67203356 @default.
- W2399136500 hasConceptScore W2399136500C77805123 @default.
- W2399136500 hasConceptScore W2399136500C97541855 @default.
- W2399136500 hasLocation W23991365001 @default.
- W2399136500 hasOpenAccess W2399136500 @default.
- W2399136500 hasPrimaryLocation W23991365001 @default.
- W2399136500 hasRelatedWork W101901138 @default.
- W2399136500 hasRelatedWork W1553476745 @default.
- W2399136500 hasRelatedWork W1591675293 @default.
- W2399136500 hasRelatedWork W1669401748 @default.
- W2399136500 hasRelatedWork W1812824539 @default.
- W2399136500 hasRelatedWork W1997816436 @default.
- W2399136500 hasRelatedWork W2017207054 @default.
- W2399136500 hasRelatedWork W2028357975 @default.
- W2399136500 hasRelatedWork W2080379318 @default.
- W2399136500 hasRelatedWork W208428353 @default.
- W2399136500 hasRelatedWork W2121779632 @default.
- W2399136500 hasRelatedWork W2143115205 @default.
- W2399136500 hasRelatedWork W225045806 @default.
- W2399136500 hasRelatedWork W2348457532 @default.
- W2399136500 hasRelatedWork W2356119859 @default.
- W2399136500 hasRelatedWork W2369463503 @default.
- W2399136500 hasRelatedWork W2491675558 @default.
- W2399136500 hasRelatedWork W2528846071 @default.
- W2399136500 hasRelatedWork W2534140487 @default.
- W2399136500 hasRelatedWork W3148138296 @default.
- W2399136500 isParatext "false" @default.
- W2399136500 isRetracted "false" @default.
- W2399136500 magId "2399136500" @default.
- W2399136500 workType "article" @default.