Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287776162> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4287776162 abstract "In this paper, we provide an overview of the existing methods for integrating human advice into a Reinforcement Learning process. We first propose a taxonomy of the different forms of advice that can be provided to a learning agent. We then describe the methods that can be used for interpreting advice when its meaning is not determined beforehand. Finally, we review different approaches for integrating advice into the learning process." @default.
- W4287776162 created "2022-07-26" @default.
- W4287776162 creator A5002179303 @default.
- W4287776162 creator A5049398785 @default.
- W4287776162 date "2020-05-22" @default.
- W4287776162 modified "2023-09-28" @default.
- W4287776162 title "Reinforcement learning with human advice: a survey" @default.
- W4287776162 doi "https://doi.org/10.48550/arxiv.2005.11016" @default.
- W4287776162 hasPublicationYear "2020" @default.
- W4287776162 type Work @default.
- W4287776162 citedByCount "0" @default.
- W4287776162 crossrefType "posted-content" @default.
- W4287776162 hasAuthorship W4287776162A5002179303 @default.
- W4287776162 hasAuthorship W4287776162A5049398785 @default.
- W4287776162 hasBestOaLocation W42877761621 @default.
- W4287776162 hasConcept C111919701 @default.
- W4287776162 hasConcept C154945302 @default.
- W4287776162 hasConcept C15744967 @default.
- W4287776162 hasConcept C199360897 @default.
- W4287776162 hasConcept C2779955035 @default.
- W4287776162 hasConcept C2780876879 @default.
- W4287776162 hasConcept C41008148 @default.
- W4287776162 hasConcept C542102704 @default.
- W4287776162 hasConcept C58642233 @default.
- W4287776162 hasConcept C59822182 @default.
- W4287776162 hasConcept C67203356 @default.
- W4287776162 hasConcept C77805123 @default.
- W4287776162 hasConcept C86803240 @default.
- W4287776162 hasConcept C97541855 @default.
- W4287776162 hasConcept C98045186 @default.
- W4287776162 hasConceptScore W4287776162C111919701 @default.
- W4287776162 hasConceptScore W4287776162C154945302 @default.
- W4287776162 hasConceptScore W4287776162C15744967 @default.
- W4287776162 hasConceptScore W4287776162C199360897 @default.
- W4287776162 hasConceptScore W4287776162C2779955035 @default.
- W4287776162 hasConceptScore W4287776162C2780876879 @default.
- W4287776162 hasConceptScore W4287776162C41008148 @default.
- W4287776162 hasConceptScore W4287776162C542102704 @default.
- W4287776162 hasConceptScore W4287776162C58642233 @default.
- W4287776162 hasConceptScore W4287776162C59822182 @default.
- W4287776162 hasConceptScore W4287776162C67203356 @default.
- W4287776162 hasConceptScore W4287776162C77805123 @default.
- W4287776162 hasConceptScore W4287776162C86803240 @default.
- W4287776162 hasConceptScore W4287776162C97541855 @default.
- W4287776162 hasConceptScore W4287776162C98045186 @default.
- W4287776162 hasLocation W42877761621 @default.
- W4287776162 hasLocation W42877761622 @default.
- W4287776162 hasLocation W42877761623 @default.
- W4287776162 hasOpenAccess W4287776162 @default.
- W4287776162 hasPrimaryLocation W42877761621 @default.
- W4287776162 hasRelatedWork W1986333311 @default.
- W4287776162 hasRelatedWork W2891655128 @default.
- W4287776162 hasRelatedWork W3005560120 @default.
- W4287776162 hasRelatedWork W3032198287 @default.
- W4287776162 hasRelatedWork W3094270515 @default.
- W4287776162 hasRelatedWork W4206669594 @default.
- W4287776162 hasRelatedWork W4210531367 @default.
- W4287776162 hasRelatedWork W4210912933 @default.
- W4287776162 hasRelatedWork W4226176818 @default.
- W4287776162 hasRelatedWork W4255994452 @default.
- W4287776162 isParatext "false" @default.
- W4287776162 isRetracted "false" @default.
- W4287776162 workType "article" @default.