Matches in SemOpenAlex for { <https://semopenalex.org/work/W2126565096> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2126565096 abstract "Temporal difference (TD) learning methods [22] have become popular reinforcement learning techniques in recent years. TD methods have had some experimental successes and have been shown to exhibit some desirable properties in theory, but have often been found very slow in practice. A key feature of TD methods is that they represent policies in terms of value functions. In this paper we introduce behavior transfer, a novel approach to speeding up TD learning by transferring the learned value function from one task to a second related task. We present experimental results showing that autonomous learners are able to learn one multiagent task and then use behavior transfer to markedly reduce the total training time for a more complex task." @default.
- W2126565096 created "2016-06-24" @default.
- W2126565096 creator A5001594330 @default.
- W2126565096 creator A5070914351 @default.
- W2126565096 date "2005-07-25" @default.
- W2126565096 modified "2023-10-18" @default.
- W2126565096 title "Behavior transfer for value-function-based reinforcement learning" @default.
- W2126565096 cites W1584313244 @default.
- W2126565096 cites W2012036715 @default.
- W2126565096 cites W2089561656 @default.
- W2126565096 cites W2119717200 @default.
- W2126565096 cites W2198041288 @default.
- W2126565096 cites W2334782222 @default.
- W2126565096 cites W3012995883 @default.
- W2126565096 cites W3211727813 @default.
- W2126565096 doi "https://doi.org/10.1145/1082473.1082482" @default.
- W2126565096 hasPublicationYear "2005" @default.
- W2126565096 type Work @default.
- W2126565096 sameAs 2126565096 @default.
- W2126565096 citedByCount "110" @default.
- W2126565096 countsByYear W21265650962012 @default.
- W2126565096 countsByYear W21265650962013 @default.
- W2126565096 countsByYear W21265650962014 @default.
- W2126565096 countsByYear W21265650962015 @default.
- W2126565096 countsByYear W21265650962016 @default.
- W2126565096 countsByYear W21265650962017 @default.
- W2126565096 countsByYear W21265650962018 @default.
- W2126565096 countsByYear W21265650962019 @default.
- W2126565096 countsByYear W21265650962020 @default.
- W2126565096 countsByYear W21265650962022 @default.
- W2126565096 countsByYear W21265650962023 @default.
- W2126565096 crossrefType "proceedings-article" @default.
- W2126565096 hasAuthorship W2126565096A5001594330 @default.
- W2126565096 hasAuthorship W2126565096A5070914351 @default.
- W2126565096 hasBestOaLocation W21265650962 @default.
- W2126565096 hasConcept C119599485 @default.
- W2126565096 hasConcept C119857082 @default.
- W2126565096 hasConcept C127413603 @default.
- W2126565096 hasConcept C138885662 @default.
- W2126565096 hasConcept C14036430 @default.
- W2126565096 hasConcept C150899416 @default.
- W2126565096 hasConcept C154945302 @default.
- W2126565096 hasConcept C15744967 @default.
- W2126565096 hasConcept C196340769 @default.
- W2126565096 hasConcept C201995342 @default.
- W2126565096 hasConcept C26517878 @default.
- W2126565096 hasConcept C2776291640 @default.
- W2126565096 hasConcept C2776401178 @default.
- W2126565096 hasConcept C2780451532 @default.
- W2126565096 hasConcept C38652104 @default.
- W2126565096 hasConcept C41008148 @default.
- W2126565096 hasConcept C41895202 @default.
- W2126565096 hasConcept C67203356 @default.
- W2126565096 hasConcept C77805123 @default.
- W2126565096 hasConcept C78458016 @default.
- W2126565096 hasConcept C81299745 @default.
- W2126565096 hasConcept C86803240 @default.
- W2126565096 hasConcept C97541855 @default.
- W2126565096 hasConceptScore W2126565096C119599485 @default.
- W2126565096 hasConceptScore W2126565096C119857082 @default.
- W2126565096 hasConceptScore W2126565096C127413603 @default.
- W2126565096 hasConceptScore W2126565096C138885662 @default.
- W2126565096 hasConceptScore W2126565096C14036430 @default.
- W2126565096 hasConceptScore W2126565096C150899416 @default.
- W2126565096 hasConceptScore W2126565096C154945302 @default.
- W2126565096 hasConceptScore W2126565096C15744967 @default.
- W2126565096 hasConceptScore W2126565096C196340769 @default.
- W2126565096 hasConceptScore W2126565096C201995342 @default.
- W2126565096 hasConceptScore W2126565096C26517878 @default.
- W2126565096 hasConceptScore W2126565096C2776291640 @default.
- W2126565096 hasConceptScore W2126565096C2776401178 @default.
- W2126565096 hasConceptScore W2126565096C2780451532 @default.
- W2126565096 hasConceptScore W2126565096C38652104 @default.
- W2126565096 hasConceptScore W2126565096C41008148 @default.
- W2126565096 hasConceptScore W2126565096C41895202 @default.
- W2126565096 hasConceptScore W2126565096C67203356 @default.
- W2126565096 hasConceptScore W2126565096C77805123 @default.
- W2126565096 hasConceptScore W2126565096C78458016 @default.
- W2126565096 hasConceptScore W2126565096C81299745 @default.
- W2126565096 hasConceptScore W2126565096C86803240 @default.
- W2126565096 hasConceptScore W2126565096C97541855 @default.
- W2126565096 hasLocation W21265650961 @default.
- W2126565096 hasLocation W21265650962 @default.
- W2126565096 hasOpenAccess W2126565096 @default.
- W2126565096 hasPrimaryLocation W21265650961 @default.
- W2126565096 hasRelatedWork W2293550301 @default.
- W2126565096 hasRelatedWork W2960456850 @default.
- W2126565096 hasRelatedWork W3021430260 @default.
- W2126565096 hasRelatedWork W4281645081 @default.
- W2126565096 hasRelatedWork W4308262314 @default.
- W2126565096 hasRelatedWork W4312200629 @default.
- W2126565096 hasRelatedWork W4319083788 @default.
- W2126565096 hasRelatedWork W4379662533 @default.
- W2126565096 hasRelatedWork W4382286161 @default.
- W2126565096 hasRelatedWork W4386213806 @default.
- W2126565096 isParatext "false" @default.
- W2126565096 isRetracted "false" @default.
- W2126565096 magId "2126565096" @default.
- W2126565096 workType "article" @default.