Matches in SemOpenAlex for { <https://semopenalex.org/work/W1520340982> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W1520340982 abstract "COACH (COrrective Advice Communicated by Humans), a new interactive learning framework that allows non-expert humans to shape a policy through corrective advice, using a binary signal in the action domain of the agent, is proposed. One of the main innovative features of COACH is a mechanism for adaptively adjusting the amount of human feedback that a given action receives, taking into consideration past feedback. The performance of COACH is compared with the one of TAMER (Teaching an Agent Manually via Evaluative Reinforcement), ACTAMER (Actor-Critic TAMER), and an autonomous agent trained using SARSA(?) in two reinforcement learning problems. COACH outperforms all other learning frameworks in the reported experiments. In addition, results show that COACH is able to transfer successfully human knowledge to agents with continuous actions, being a complementary approach to TAMER, which is appropriate for teaching in discrete action domains." @default.
- W1520340982 created "2016-06-24" @default.
- W1520340982 creator A5028010633 @default.
- W1520340982 creator A5048448415 @default.
- W1520340982 date "2015-07-01" @default.
- W1520340982 modified "2023-09-23" @default.
- W1520340982 title "COACH: Learning continuous actions from COrrective Advice Communicated by Humans" @default.
- W1520340982 cites W1626155273 @default.
- W1520340982 cites W1966259872 @default.
- W1520340982 cites W1979308911 @default.
- W1520340982 cites W1986014385 @default.
- W1520340982 cites W1999874108 @default.
- W1520340982 cites W2062821321 @default.
- W1520340982 cites W2098584016 @default.
- W1520340982 cites W2108503630 @default.
- W1520340982 cites W2110064869 @default.
- W1520340982 cites W2120982521 @default.
- W1520340982 cites W2128103053 @default.
- W1520340982 cites W2129659607 @default.
- W1520340982 cites W2150818585 @default.
- W1520340982 cites W2154018708 @default.
- W1520340982 cites W2156869222 @default.
- W1520340982 cites W2162932021 @default.
- W1520340982 doi "https://doi.org/10.1109/icar.2015.7251514" @default.
- W1520340982 hasPublicationYear "2015" @default.
- W1520340982 type Work @default.
- W1520340982 sameAs 1520340982 @default.
- W1520340982 citedByCount "15" @default.
- W1520340982 countsByYear W15203409822016 @default.
- W1520340982 countsByYear W15203409822018 @default.
- W1520340982 countsByYear W15203409822019 @default.
- W1520340982 countsByYear W15203409822020 @default.
- W1520340982 countsByYear W15203409822021 @default.
- W1520340982 countsByYear W15203409822022 @default.
- W1520340982 countsByYear W15203409822023 @default.
- W1520340982 crossrefType "proceedings-article" @default.
- W1520340982 hasAuthorship W1520340982A5028010633 @default.
- W1520340982 hasAuthorship W1520340982A5048448415 @default.
- W1520340982 hasConcept C107457646 @default.
- W1520340982 hasConcept C121332964 @default.
- W1520340982 hasConcept C134306372 @default.
- W1520340982 hasConcept C145420912 @default.
- W1520340982 hasConcept C150899416 @default.
- W1520340982 hasConcept C154945302 @default.
- W1520340982 hasConcept C15744967 @default.
- W1520340982 hasConcept C199360897 @default.
- W1520340982 hasConcept C207685749 @default.
- W1520340982 hasConcept C2779305910 @default.
- W1520340982 hasConcept C2779955035 @default.
- W1520340982 hasConcept C2780791683 @default.
- W1520340982 hasConcept C33923547 @default.
- W1520340982 hasConcept C36503486 @default.
- W1520340982 hasConcept C41008148 @default.
- W1520340982 hasConcept C62520636 @default.
- W1520340982 hasConcept C97541855 @default.
- W1520340982 hasConceptScore W1520340982C107457646 @default.
- W1520340982 hasConceptScore W1520340982C121332964 @default.
- W1520340982 hasConceptScore W1520340982C134306372 @default.
- W1520340982 hasConceptScore W1520340982C145420912 @default.
- W1520340982 hasConceptScore W1520340982C150899416 @default.
- W1520340982 hasConceptScore W1520340982C154945302 @default.
- W1520340982 hasConceptScore W1520340982C15744967 @default.
- W1520340982 hasConceptScore W1520340982C199360897 @default.
- W1520340982 hasConceptScore W1520340982C207685749 @default.
- W1520340982 hasConceptScore W1520340982C2779305910 @default.
- W1520340982 hasConceptScore W1520340982C2779955035 @default.
- W1520340982 hasConceptScore W1520340982C2780791683 @default.
- W1520340982 hasConceptScore W1520340982C33923547 @default.
- W1520340982 hasConceptScore W1520340982C36503486 @default.
- W1520340982 hasConceptScore W1520340982C41008148 @default.
- W1520340982 hasConceptScore W1520340982C62520636 @default.
- W1520340982 hasConceptScore W1520340982C97541855 @default.
- W1520340982 hasLocation W15203409821 @default.
- W1520340982 hasOpenAccess W1520340982 @default.
- W1520340982 hasPrimaryLocation W15203409821 @default.
- W1520340982 hasRelatedWork W1483849531 @default.
- W1520340982 hasRelatedWork W15218170 @default.
- W1520340982 hasRelatedWork W1991466308 @default.
- W1520340982 hasRelatedWork W2398715346 @default.
- W1520340982 hasRelatedWork W2739083961 @default.
- W1520340982 hasRelatedWork W2963611966 @default.
- W1520340982 hasRelatedWork W3130762189 @default.
- W1520340982 hasRelatedWork W3209094908 @default.
- W1520340982 hasRelatedWork W4287327031 @default.
- W1520340982 hasRelatedWork W605348272 @default.
- W1520340982 isParatext "false" @default.
- W1520340982 isRetracted "false" @default.
- W1520340982 magId "1520340982" @default.
- W1520340982 workType "article" @default.