Matches in SemOpenAlex for { <https://semopenalex.org/work/W2550648340> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2550648340 abstract "Reinforcement learning is a powerful machine learning paradigm that allows agents to autonomously learn to maximize a scalar reward. However, it often suffers from poor initial performance and long learning times. This paper discusses how collecting on-line human feedback, both in real time and post hoc, can potentially improve the performance of such learning systems. We use the game Pac-Man to simulate a navigation setting and show that workers are able to accurately identify both when a sub-optimal action is executed, and what action should have been performed instead. Our results demonstrate that the crowd is capable of generating helpful input. We conclude with a discussion the types of errors that occur most commonly when engaging human workers for this task, and a discussion of how such data could be used to improve learning. Our work serves as a critical first step in designing systems that use real-time human feedback to improve the learning performance of automated systems on-the-fly." @default.
- W2550648340 created "2016-11-30" @default.
- W2550648340 creator A5012361632 @default.
- W2550648340 creator A5044705843 @default.
- W2550648340 creator A5063574664 @default.
- W2550648340 creator A5070914351 @default.
- W2550648340 date "2015-01-01" @default.
- W2550648340 modified "2023-09-24" @default.
- W2550648340 title "Generating real-time crowd advice to improve reinforcement learning agents" @default.
- W2550648340 cites W121023703 @default.
- W2550648340 cites W1505937442 @default.
- W2550648340 cites W1539975474 @default.
- W2550648340 cites W1777239053 @default.
- W2550648340 cites W1949804828 @default.
- W2550648340 cites W1969685488 @default.
- W2550648340 cites W1986014385 @default.
- W2550648340 cites W2009504203 @default.
- W2550648340 cites W2070301851 @default.
- W2550648340 cites W2088664555 @default.
- W2550648340 cites W2116157560 @default.
- W2550648340 cites W2137375617 @default.
- W2550648340 cites W2138847321 @default.
- W2550648340 cites W2141904310 @default.
- W2550648340 cites W2169659168 @default.
- W2550648340 cites W2903158431 @default.
- W2550648340 cites W745775011 @default.
- W2550648340 cites W2131600418 @default.
- W2550648340 hasPublicationYear "2015" @default.
- W2550648340 type Work @default.
- W2550648340 sameAs 2550648340 @default.
- W2550648340 citedByCount "1" @default.
- W2550648340 countsByYear W25506483402015 @default.
- W2550648340 crossrefType "proceedings-article" @default.
- W2550648340 hasAuthorship W2550648340A5012361632 @default.
- W2550648340 hasAuthorship W2550648340A5044705843 @default.
- W2550648340 hasAuthorship W2550648340A5063574664 @default.
- W2550648340 hasAuthorship W2550648340A5070914351 @default.
- W2550648340 hasConcept C107457646 @default.
- W2550648340 hasConcept C111919701 @default.
- W2550648340 hasConcept C119857082 @default.
- W2550648340 hasConcept C121332964 @default.
- W2550648340 hasConcept C127413603 @default.
- W2550648340 hasConcept C154945302 @default.
- W2550648340 hasConcept C188888258 @default.
- W2550648340 hasConcept C19966478 @default.
- W2550648340 hasConcept C201995342 @default.
- W2550648340 hasConcept C2780451532 @default.
- W2550648340 hasConcept C2780791683 @default.
- W2550648340 hasConcept C2781020372 @default.
- W2550648340 hasConcept C41008148 @default.
- W2550648340 hasConcept C62520636 @default.
- W2550648340 hasConcept C90509273 @default.
- W2550648340 hasConcept C97541855 @default.
- W2550648340 hasConceptScore W2550648340C107457646 @default.
- W2550648340 hasConceptScore W2550648340C111919701 @default.
- W2550648340 hasConceptScore W2550648340C119857082 @default.
- W2550648340 hasConceptScore W2550648340C121332964 @default.
- W2550648340 hasConceptScore W2550648340C127413603 @default.
- W2550648340 hasConceptScore W2550648340C154945302 @default.
- W2550648340 hasConceptScore W2550648340C188888258 @default.
- W2550648340 hasConceptScore W2550648340C19966478 @default.
- W2550648340 hasConceptScore W2550648340C201995342 @default.
- W2550648340 hasConceptScore W2550648340C2780451532 @default.
- W2550648340 hasConceptScore W2550648340C2780791683 @default.
- W2550648340 hasConceptScore W2550648340C2781020372 @default.
- W2550648340 hasConceptScore W2550648340C41008148 @default.
- W2550648340 hasConceptScore W2550648340C62520636 @default.
- W2550648340 hasConceptScore W2550648340C90509273 @default.
- W2550648340 hasConceptScore W2550648340C97541855 @default.
- W2550648340 hasLocation W25506483401 @default.
- W2550648340 hasOpenAccess W2550648340 @default.
- W2550648340 hasPrimaryLocation W25506483401 @default.
- W2550648340 hasRelatedWork W2272929109 @default.
- W2550648340 hasRelatedWork W2344013593 @default.
- W2550648340 hasRelatedWork W2397581010 @default.
- W2550648340 hasRelatedWork W2522275265 @default.
- W2550648340 hasRelatedWork W2535652371 @default.
- W2550648340 hasRelatedWork W2784165037 @default.
- W2550648340 hasRelatedWork W2802166897 @default.
- W2550648340 hasRelatedWork W2903630557 @default.
- W2550648340 hasRelatedWork W2914584948 @default.
- W2550648340 hasRelatedWork W2968652061 @default.
- W2550648340 hasRelatedWork W2984869362 @default.
- W2550648340 hasRelatedWork W2999490157 @default.
- W2550648340 hasRelatedWork W3005607450 @default.
- W2550648340 hasRelatedWork W3037425117 @default.
- W2550648340 hasRelatedWork W3098815154 @default.
- W2550648340 hasRelatedWork W3149922422 @default.
- W2550648340 hasRelatedWork W3155541343 @default.
- W2550648340 hasRelatedWork W3167658443 @default.
- W2550648340 hasRelatedWork W3186326521 @default.
- W2550648340 hasRelatedWork W2183893812 @default.
- W2550648340 isParatext "false" @default.
- W2550648340 isRetracted "false" @default.
- W2550648340 magId "2550648340" @default.
- W2550648340 workType "article" @default.