Matches in SemOpenAlex for { <https://semopenalex.org/work/W3135821167> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3135821167 abstract "When a robot is deployed to learn a new task in a real-word environment, there may be multiple teachers and therefore multiple sources of feedback. Furthermore, there may be multiple optimal solutions for a given task and teachers may have preferences among those various solutions. We present an Interactive Reinforcement Learning (I-RL) algorithm, Multi-Teacher Activated Policy Shaping (M-TAPS), which addresses the problem of learning from multiple teachers and leverages differences between them as a means to explore the environment. We show that this algorithm can significantly increase an agent's robustness to the environment and quickly adopt to a teacher's preferences. Finally, we present a formal model for comparing human teachers and constructed oracle teachers and the way that they provide feedback to a robot." @default.
- W3135821167 created "2021-03-15" @default.
- W3135821167 creator A5070000164 @default.
- W3135821167 creator A5077011363 @default.
- W3135821167 date "2021-03-08" @default.
- W3135821167 modified "2023-09-26" @default.
- W3135821167 title "When Oracles Go Wrong: Using Preferences as a Means to Explore" @default.
- W3135821167 cites W1991618009 @default.
- W3135821167 cites W2156869222 @default.
- W3135821167 cites W2909713847 @default.
- W3135821167 cites W3101754927 @default.
- W3135821167 cites W4288083537 @default.
- W3135821167 doi "https://doi.org/10.1145/3434074.3447189" @default.
- W3135821167 hasPublicationYear "2021" @default.
- W3135821167 type Work @default.
- W3135821167 sameAs 3135821167 @default.
- W3135821167 citedByCount "0" @default.
- W3135821167 crossrefType "proceedings-article" @default.
- W3135821167 hasAuthorship W3135821167A5070000164 @default.
- W3135821167 hasAuthorship W3135821167A5077011363 @default.
- W3135821167 hasBestOaLocation W31358211671 @default.
- W3135821167 hasConcept C104317684 @default.
- W3135821167 hasConcept C107457646 @default.
- W3135821167 hasConcept C115903868 @default.
- W3135821167 hasConcept C127413603 @default.
- W3135821167 hasConcept C154945302 @default.
- W3135821167 hasConcept C185592680 @default.
- W3135821167 hasConcept C201995342 @default.
- W3135821167 hasConcept C2780451532 @default.
- W3135821167 hasConcept C41008148 @default.
- W3135821167 hasConcept C55166926 @default.
- W3135821167 hasConcept C55493867 @default.
- W3135821167 hasConcept C63479239 @default.
- W3135821167 hasConcept C90509273 @default.
- W3135821167 hasConcept C97541855 @default.
- W3135821167 hasConceptScore W3135821167C104317684 @default.
- W3135821167 hasConceptScore W3135821167C107457646 @default.
- W3135821167 hasConceptScore W3135821167C115903868 @default.
- W3135821167 hasConceptScore W3135821167C127413603 @default.
- W3135821167 hasConceptScore W3135821167C154945302 @default.
- W3135821167 hasConceptScore W3135821167C185592680 @default.
- W3135821167 hasConceptScore W3135821167C201995342 @default.
- W3135821167 hasConceptScore W3135821167C2780451532 @default.
- W3135821167 hasConceptScore W3135821167C41008148 @default.
- W3135821167 hasConceptScore W3135821167C55166926 @default.
- W3135821167 hasConceptScore W3135821167C55493867 @default.
- W3135821167 hasConceptScore W3135821167C63479239 @default.
- W3135821167 hasConceptScore W3135821167C90509273 @default.
- W3135821167 hasConceptScore W3135821167C97541855 @default.
- W3135821167 hasLocation W31358211671 @default.
- W3135821167 hasOpenAccess W3135821167 @default.
- W3135821167 hasPrimaryLocation W31358211671 @default.
- W3135821167 hasRelatedWork W1763389228 @default.
- W3135821167 hasRelatedWork W2007682987 @default.
- W3135821167 hasRelatedWork W2079554071 @default.
- W3135821167 hasRelatedWork W2144821713 @default.
- W3135821167 hasRelatedWork W2162746924 @default.
- W3135821167 hasRelatedWork W2166791242 @default.
- W3135821167 hasRelatedWork W2323122434 @default.
- W3135821167 hasRelatedWork W2343019076 @default.
- W3135821167 hasRelatedWork W3038859464 @default.
- W3135821167 hasRelatedWork W3040778547 @default.
- W3135821167 isParatext "false" @default.
- W3135821167 isRetracted "false" @default.
- W3135821167 magId "3135821167" @default.
- W3135821167 workType "article" @default.