Matches in SemOpenAlex for { <https://semopenalex.org/work/W123280120> ?p ?o ?g. }
- W123280120 endingPage "433" @default.
- W123280120 startingPage "428" @default.
- W123280120 abstract "We present the novel Kernel Rewards Regression (KRR) method for Policy Iteration in Reinforcement Learning on continuous state domains. Our method is able to obtain very useful policies observing just a few state action transitions. It considers the Reinforcement Learning problem as a regression task for which any appropriate technique may be applied. The use of kernel methods, e.g. the Support Vector Machine, enables the user to incorporate different types of structural prior knowledge about the state space by redefining the inner product. Furthermore KRR is a completely Off-policy method. The observations may be constructed by any sufficiently exploring policy, even the fully random one. We tested the algorithm on three typical Reinforcement Learning benchmarks. Moreover we give a proof for the correctness of our model and an error bound for estimating the Q-functions." @default.
- W123280120 created "2016-06-24" @default.
- W123280120 creator A5014856404 @default.
- W123280120 creator A5035246650 @default.
- W123280120 creator A5072736085 @default.
- W123280120 date "2006-02-13" @default.
- W123280120 modified "2023-09-23" @default.
- W123280120 title "Kernel rewards regression: an information efficient batch policy iteration approach" @default.
- W123280120 cites W1494575750 @default.
- W123280120 cites W1505888104 @default.
- W123280120 cites W1512098439 @default.
- W123280120 cites W1515851193 @default.
- W123280120 cites W1518494348 @default.
- W123280120 cites W1550698229 @default.
- W123280120 cites W1563088657 @default.
- W123280120 cites W1570106308 @default.
- W123280120 cites W1580425441 @default.
- W123280120 cites W1592847719 @default.
- W123280120 cites W1597303641 @default.
- W123280120 cites W1777239053 @default.
- W123280120 cites W1964357740 @default.
- W123280120 cites W2047028564 @default.
- W123280120 cites W2099833070 @default.
- W123280120 cites W2106451198 @default.
- W123280120 cites W2121649666 @default.
- W123280120 cites W2121863487 @default.
- W123280120 cites W2123818990 @default.
- W123280120 cites W2130005627 @default.
- W123280120 cites W2130031702 @default.
- W123280120 cites W2148603752 @default.
- W123280120 cites W2154175369 @default.
- W123280120 cites W2156909104 @default.
- W123280120 cites W2168353336 @default.
- W123280120 cites W2171388298 @default.
- W123280120 cites W2312609093 @default.
- W123280120 cites W342858109 @default.
- W123280120 hasPublicationYear "2006" @default.
- W123280120 type Work @default.
- W123280120 sameAs 123280120 @default.
- W123280120 citedByCount "4" @default.
- W123280120 countsByYear W1232801202013 @default.
- W123280120 crossrefType "proceedings-article" @default.
- W123280120 hasAuthorship W123280120A5014856404 @default.
- W123280120 hasAuthorship W123280120A5035246650 @default.
- W123280120 hasAuthorship W123280120A5072736085 @default.
- W123280120 hasConcept C105795698 @default.
- W123280120 hasConcept C11413529 @default.
- W123280120 hasConcept C114614502 @default.
- W123280120 hasConcept C119857082 @default.
- W123280120 hasConcept C122280245 @default.
- W123280120 hasConcept C12267149 @default.
- W123280120 hasConcept C154945302 @default.
- W123280120 hasConcept C160446489 @default.
- W123280120 hasConcept C33923547 @default.
- W123280120 hasConcept C41008148 @default.
- W123280120 hasConcept C48103436 @default.
- W123280120 hasConcept C55439883 @default.
- W123280120 hasConcept C72434380 @default.
- W123280120 hasConcept C74193536 @default.
- W123280120 hasConcept C83546350 @default.
- W123280120 hasConcept C97541855 @default.
- W123280120 hasConceptScore W123280120C105795698 @default.
- W123280120 hasConceptScore W123280120C11413529 @default.
- W123280120 hasConceptScore W123280120C114614502 @default.
- W123280120 hasConceptScore W123280120C119857082 @default.
- W123280120 hasConceptScore W123280120C122280245 @default.
- W123280120 hasConceptScore W123280120C12267149 @default.
- W123280120 hasConceptScore W123280120C154945302 @default.
- W123280120 hasConceptScore W123280120C160446489 @default.
- W123280120 hasConceptScore W123280120C33923547 @default.
- W123280120 hasConceptScore W123280120C41008148 @default.
- W123280120 hasConceptScore W123280120C48103436 @default.
- W123280120 hasConceptScore W123280120C55439883 @default.
- W123280120 hasConceptScore W123280120C72434380 @default.
- W123280120 hasConceptScore W123280120C74193536 @default.
- W123280120 hasConceptScore W123280120C83546350 @default.
- W123280120 hasConceptScore W123280120C97541855 @default.
- W123280120 hasOpenAccess W123280120 @default.
- W123280120 hasRelatedWork W1489912246 @default.
- W123280120 hasRelatedWork W1603605173 @default.
- W123280120 hasRelatedWork W1840881174 @default.
- W123280120 hasRelatedWork W1984988829 @default.
- W123280120 hasRelatedWork W2073242129 @default.
- W123280120 hasRelatedWork W2100024763 @default.
- W123280120 hasRelatedWork W2115951219 @default.
- W123280120 hasRelatedWork W2121863487 @default.
- W123280120 hasRelatedWork W2144655553 @default.
- W123280120 hasRelatedWork W2154023516 @default.
- W123280120 hasRelatedWork W2160095661 @default.
- W123280120 hasRelatedWork W2166265228 @default.
- W123280120 hasRelatedWork W2195535662 @default.
- W123280120 hasRelatedWork W2378547035 @default.
- W123280120 hasRelatedWork W2389511778 @default.
- W123280120 hasRelatedWork W2599481709 @default.
- W123280120 hasRelatedWork W2797427442 @default.
- W123280120 hasRelatedWork W2899685447 @default.
- W123280120 hasRelatedWork W3184838181 @default.
- W123280120 hasRelatedWork W3209208698 @default.