Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288093757> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4288093757 abstract "Robots can learn the right reward function by querying a human expert. Existing approaches attempt to choose questions where the robot is most uncertain about the human's response; however, they do not consider how easy it will be for the human to answer! In this paper we explore an information gain formulation for optimally selecting questions that naturally account for the human's ability to answer. Our approach identifies questions that optimize the trade-off between robot and human uncertainty, and determines when these questions become redundant or costly. Simulations and a user study show our method not only produces easy questions, but also ultimately results in faster reward learning." @default.
- W4288093757 created "2022-07-28" @default.
- W4288093757 creator A5026703888 @default.
- W4288093757 creator A5031426401 @default.
- W4288093757 creator A5063608480 @default.
- W4288093757 creator A5074251295 @default.
- W4288093757 creator A5080725225 @default.
- W4288093757 date "2019-10-10" @default.
- W4288093757 modified "2023-09-27" @default.
- W4288093757 title "Asking Easy Questions: A User-Friendly Approach to Active Reward Learning" @default.
- W4288093757 doi "https://doi.org/10.48550/arxiv.1910.04365" @default.
- W4288093757 hasPublicationYear "2019" @default.
- W4288093757 type Work @default.
- W4288093757 citedByCount "0" @default.
- W4288093757 crossrefType "posted-content" @default.
- W4288093757 hasAuthorship W4288093757A5026703888 @default.
- W4288093757 hasAuthorship W4288093757A5031426401 @default.
- W4288093757 hasAuthorship W4288093757A5063608480 @default.
- W4288093757 hasAuthorship W4288093757A5074251295 @default.
- W4288093757 hasAuthorship W4288093757A5080725225 @default.
- W4288093757 hasBestOaLocation W42880937571 @default.
- W4288093757 hasConcept C107457646 @default.
- W4288093757 hasConcept C111919701 @default.
- W4288093757 hasConcept C119857082 @default.
- W4288093757 hasConcept C14036430 @default.
- W4288093757 hasConcept C154945302 @default.
- W4288093757 hasConcept C41008148 @default.
- W4288093757 hasConcept C61437842 @default.
- W4288093757 hasConcept C78458016 @default.
- W4288093757 hasConcept C86803240 @default.
- W4288093757 hasConcept C90509273 @default.
- W4288093757 hasConceptScore W4288093757C107457646 @default.
- W4288093757 hasConceptScore W4288093757C111919701 @default.
- W4288093757 hasConceptScore W4288093757C119857082 @default.
- W4288093757 hasConceptScore W4288093757C14036430 @default.
- W4288093757 hasConceptScore W4288093757C154945302 @default.
- W4288093757 hasConceptScore W4288093757C41008148 @default.
- W4288093757 hasConceptScore W4288093757C61437842 @default.
- W4288093757 hasConceptScore W4288093757C78458016 @default.
- W4288093757 hasConceptScore W4288093757C86803240 @default.
- W4288093757 hasConceptScore W4288093757C90509273 @default.
- W4288093757 hasLocation W42880937571 @default.
- W4288093757 hasOpenAccess W4288093757 @default.
- W4288093757 hasPrimaryLocation W42880937571 @default.
- W4288093757 hasRelatedWork W2961085424 @default.
- W4288093757 hasRelatedWork W3046775127 @default.
- W4288093757 hasRelatedWork W3170094116 @default.
- W4288093757 hasRelatedWork W4205820585 @default.
- W4288093757 hasRelatedWork W4205958290 @default.
- W4288093757 hasRelatedWork W4285260836 @default.
- W4288093757 hasRelatedWork W4286629047 @default.
- W4288093757 hasRelatedWork W4306321456 @default.
- W4288093757 hasRelatedWork W4306674287 @default.
- W4288093757 hasRelatedWork W4224009465 @default.
- W4288093757 isParatext "false" @default.
- W4288093757 isRetracted "false" @default.
- W4288093757 workType "article" @default.