Matches in SemOpenAlex for { <https://semopenalex.org/work/W2182103321> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2182103321 endingPage "709" @default.
- W2182103321 startingPage "703" @default.
- W2182103321 abstract "AbstractReinforcement learning (RL) is a powerful technique for learning in domains where there is no instructive feedback but only evaluative feedback and is rapidly expanding in industrial and research fields. One of the main limitations of RL is the slowness in convergence. Thus, several methods have been proposed to speed up RL. They involve the incorporation of prior knowledge or bias into RL. In this paper, we present a new method for incorporating bias into RL. This method extends the choosing initial Q-values method proposed by Hailu G. and Sommer G. and one kind of learning mechanism is introduced into agent. This allows for much more specific information to guide the agent which action to choose and meanwhile it is helpful to reduce the state research space. So it improves the learning performance and speed up the convergence of the learning process greatly.KeywordsReinforcement learningprior knowledgebiasQ-learningbiasing Q-learning" @default.
- W2182103321 created "2016-06-24" @default.
- W2182103321 creator A5037465848 @default.
- W2182103321 creator A5042096631 @default.
- W2182103321 creator A5043253743 @default.
- W2182103321 creator A5050184745 @default.
- W2182103321 date "2011-01-01" @default.
- W2182103321 modified "2023-09-26" @default.
- W2182103321 title "Principled Methods for Biasing Reinforcement Learning Agents" @default.
- W2182103321 cites W2123354780 @default.
- W2182103321 cites W89091142 @default.
- W2182103321 doi "https://doi.org/10.1007/978-3-642-23887-1_89" @default.
- W2182103321 hasPublicationYear "2011" @default.
- W2182103321 type Work @default.
- W2182103321 sameAs 2182103321 @default.
- W2182103321 citedByCount "0" @default.
- W2182103321 crossrefType "book-chapter" @default.
- W2182103321 hasAuthorship W2182103321A5037465848 @default.
- W2182103321 hasAuthorship W2182103321A5042096631 @default.
- W2182103321 hasAuthorship W2182103321A5043253743 @default.
- W2182103321 hasAuthorship W2182103321A5050184745 @default.
- W2182103321 hasConcept C111919701 @default.
- W2182103321 hasConcept C11940443 @default.
- W2182103321 hasConcept C119857082 @default.
- W2182103321 hasConcept C121332964 @default.
- W2182103321 hasConcept C154945302 @default.
- W2182103321 hasConcept C162324750 @default.
- W2182103321 hasConcept C2777303404 @default.
- W2182103321 hasConcept C41008148 @default.
- W2182103321 hasConcept C50522688 @default.
- W2182103321 hasConcept C62520636 @default.
- W2182103321 hasConcept C97541855 @default.
- W2182103321 hasConcept C98045186 @default.
- W2182103321 hasConceptScore W2182103321C111919701 @default.
- W2182103321 hasConceptScore W2182103321C11940443 @default.
- W2182103321 hasConceptScore W2182103321C119857082 @default.
- W2182103321 hasConceptScore W2182103321C121332964 @default.
- W2182103321 hasConceptScore W2182103321C154945302 @default.
- W2182103321 hasConceptScore W2182103321C162324750 @default.
- W2182103321 hasConceptScore W2182103321C2777303404 @default.
- W2182103321 hasConceptScore W2182103321C41008148 @default.
- W2182103321 hasConceptScore W2182103321C50522688 @default.
- W2182103321 hasConceptScore W2182103321C62520636 @default.
- W2182103321 hasConceptScore W2182103321C97541855 @default.
- W2182103321 hasConceptScore W2182103321C98045186 @default.
- W2182103321 hasLocation W21821033211 @default.
- W2182103321 hasOpenAccess W2182103321 @default.
- W2182103321 hasPrimaryLocation W21821033211 @default.
- W2182103321 hasRelatedWork W168011852 @default.
- W2182103321 hasRelatedWork W1801951617 @default.
- W2182103321 hasRelatedWork W1985881603 @default.
- W2182103321 hasRelatedWork W2014512216 @default.
- W2182103321 hasRelatedWork W2029482943 @default.
- W2182103321 hasRelatedWork W2030008266 @default.
- W2182103321 hasRelatedWork W2050504137 @default.
- W2182103321 hasRelatedWork W2123354780 @default.
- W2182103321 hasRelatedWork W2154023516 @default.
- W2182103321 hasRelatedWork W2289410116 @default.
- W2182103321 hasRelatedWork W2354184506 @default.
- W2182103321 hasRelatedWork W2356358603 @default.
- W2182103321 hasRelatedWork W2383562610 @default.
- W2182103321 hasRelatedWork W2534140487 @default.
- W2182103321 hasRelatedWork W2557003457 @default.
- W2182103321 hasRelatedWork W2910568379 @default.
- W2182103321 hasRelatedWork W2936107880 @default.
- W2182103321 hasRelatedWork W3011697356 @default.
- W2182103321 hasRelatedWork W3107195816 @default.
- W2182103321 hasRelatedWork W3203418126 @default.
- W2182103321 isParatext "false" @default.
- W2182103321 isRetracted "false" @default.
- W2182103321 magId "2182103321" @default.
- W2182103321 workType "book-chapter" @default.