FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1888002310> ?p ?o ?g. }

• W1888002310 endingPage "848" @default.
• W1888002310 startingPage "826" @default.
• W1888002310 abstract "In this work, we address a relatively unexplored aspect of designing agents that learn from human reward. We investigate how an agent’s non-task behavior can affect a human trainer’s training and agent learning. We use the TAMER framework, which facilitates the training of agents by human-generated reward signals, i.e., judgements of the quality of the agent’s actions, as the foundation for our investigation. Then, starting from the premise that the interaction between the agent and the trainer should be bi-directional, we propose two new training interfaces to increase a human trainer’s active involvement in the training process and thereby improve the agent’s task performance. One provides information on the agent’s uncertainty which is a metric calculated as data coverage, the other on its performance. Our results from a 51-subject user study show that these interfaces can induce the trainers to train longer and give more feedback. The agent’s performance, however, increases only in response to the addition of performance-oriented information, not by sharing uncertainty levels. These results suggest that the organizational maxim about human behavior, “you get what you measure”—i.e., sharing metrics with people causes them to focus on optimizing those metrics while de-emphasizing other objectives—also applies to the training of agents. Using principle component analysis, we show how trainers in the two conditions train agents differently. In addition, by simulating the influence of the agent’s uncertainty–informative behavior on a human’s training behavior, we show that trainers could be distracted by the agent sharing its uncertainty levels about its actions, giving poor feedback for the sake of reducing the agent’s uncertainty without improving the agent’s performance." @default.
• W1888002310 created "2016-06-24" @default.
• W1888002310 creator A5043701064 @default.
• W1888002310 creator A5056649746 @default.
• W1888002310 creator A5056879203 @default.
• W1888002310 creator A5061353073 @default.
• W1888002310 date "2015-08-22" @default.
• W1888002310 modified "2023-09-26" @default.
• W1888002310 title "Using informative behavior to increase engagement while learning from human reward" @default.
• W1888002310 cites W1536323281 @default.
• W1888002310 cites W1539975474 @default.
• W1888002310 cites W1976994271 @default.
• W1888002310 cites W1986014385 @default.
• W1888002310 cites W1997458507 @default.
• W1888002310 cites W1999874108 @default.
• W1888002310 cites W2003011075 @default.
• W1888002310 cites W2088656029 @default.
• W1888002310 cites W2098584016 @default.
• W1888002310 cites W2107574152 @default.
• W1888002310 cites W2115330428 @default.
• W1888002310 cites W2118756286 @default.
• W1888002310 cites W2119388568 @default.
• W1888002310 cites W2121110499 @default.
• W1888002310 cites W2123859855 @default.
• W1888002310 cites W2129659607 @default.
• W1888002310 cites W2132504164 @default.
• W1888002310 cites W2154018708 @default.
• W1888002310 cites W2154633587 @default.
• W1888002310 cites W2156869222 @default.
• W1888002310 cites W2157174816 @default.
• W1888002310 cites W2157726050 @default.
• W1888002310 cites W4205342759 @default.
• W1888002310 cites W8222043 @default.
• W1888002310 doi "https://doi.org/10.1007/s10458-015-9308-2" @default.
• W1888002310 hasPublicationYear "2015" @default.
• W1888002310 type Work @default.
• W1888002310 sameAs 1888002310 @default.
• W1888002310 citedByCount "17" @default.
• W1888002310 countsByYear W18880023102016 @default.
• W1888002310 countsByYear W18880023102018 @default.
• W1888002310 countsByYear W18880023102019 @default.
• W1888002310 countsByYear W18880023102020 @default.
• W1888002310 countsByYear W18880023102021 @default.
• W1888002310 countsByYear W18880023102022 @default.
• W1888002310 crossrefType "journal-article" @default.
• W1888002310 hasAuthorship W1888002310A5043701064 @default.
• W1888002310 hasAuthorship W1888002310A5056649746 @default.
• W1888002310 hasAuthorship W1888002310A5056879203 @default.
• W1888002310 hasAuthorship W1888002310A5061353073 @default.
• W1888002310 hasBestOaLocation W18880023101 @default.
• W1888002310 hasConcept C107457646 @default.
• W1888002310 hasConcept C111472728 @default.
• W1888002310 hasConcept C111919701 @default.
• W1888002310 hasConcept C127413603 @default.
• W1888002310 hasConcept C138885662 @default.
• W1888002310 hasConcept C154945302 @default.
• W1888002310 hasConcept C199360897 @default.
• W1888002310 hasConcept C201995342 @default.
• W1888002310 hasConcept C2778023277 @default.
• W1888002310 hasConcept C2779530757 @default.
• W1888002310 hasConcept C2780451532 @default.
• W1888002310 hasConcept C2780463512 @default.
• W1888002310 hasConcept C41008148 @default.
• W1888002310 hasConcept C41895202 @default.
• W1888002310 hasConcept C56739046 @default.
• W1888002310 hasConcept C98045186 @default.
• W1888002310 hasConceptScore W1888002310C107457646 @default.
• W1888002310 hasConceptScore W1888002310C111472728 @default.
• W1888002310 hasConceptScore W1888002310C111919701 @default.
• W1888002310 hasConceptScore W1888002310C127413603 @default.
• W1888002310 hasConceptScore W1888002310C138885662 @default.
• W1888002310 hasConceptScore W1888002310C154945302 @default.
• W1888002310 hasConceptScore W1888002310C199360897 @default.
• W1888002310 hasConceptScore W1888002310C201995342 @default.
• W1888002310 hasConceptScore W1888002310C2778023277 @default.
• W1888002310 hasConceptScore W1888002310C2779530757 @default.
• W1888002310 hasConceptScore W1888002310C2780451532 @default.
• W1888002310 hasConceptScore W1888002310C2780463512 @default.
• W1888002310 hasConceptScore W1888002310C41008148 @default.
• W1888002310 hasConceptScore W1888002310C41895202 @default.
• W1888002310 hasConceptScore W1888002310C56739046 @default.
• W1888002310 hasConceptScore W1888002310C98045186 @default.
• W1888002310 hasFunder F4320322725 @default.
• W1888002310 hasIssue "5" @default.
• W1888002310 hasLocation W18880023101 @default.
• W1888002310 hasLocation W18880023102 @default.
• W1888002310 hasLocation W18880023103 @default.
• W1888002310 hasOpenAccess W1888002310 @default.
• W1888002310 hasPrimaryLocation W18880023101 @default.
• W1888002310 hasRelatedWork W2003033467 @default.
• W1888002310 hasRelatedWork W2081647779 @default.
• W1888002310 hasRelatedWork W2089323465 @default.
• W1888002310 hasRelatedWork W2351914136 @default.
• W1888002310 hasRelatedWork W2361218558 @default.
• W1888002310 hasRelatedWork W2361979572 @default.
• W1888002310 hasRelatedWork W2389170047 @default.
• W1888002310 hasRelatedWork W292902006 @default.
• W1888002310 hasRelatedWork W4237750775 @default.

• next