Matches in SemOpenAlex for { <https://semopenalex.org/work/W2986543994> ?p ?o ?g. }
- W2986543994 abstract "Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language about how to solve the task. We extend this one-directional communication by a one-bit communication channel from the learner back to the guide: It is able to ask the guide for help, and we limit the guidance by penalizing the learner for these requests. During training, the agent learns to control this gate based on its current observation. We find that the amount of requested guidance decreases over time and guidance is requested in situations of high uncertainty. We investigate the agent’s performance in cases of open and closed gates and discuss potential motives for the observed gating behavior." @default.
- W2986543994 created "2019-11-22" @default.
- W2986543994 creator A5007465102 @default.
- W2986543994 creator A5012032714 @default.
- W2986543994 creator A5013539443 @default.
- W2986543994 creator A5030844531 @default.
- W2986543994 creator A5041418006 @default.
- W2986543994 creator A5045425275 @default.
- W2986543994 creator A5052695225 @default.
- W2986543994 creator A5060248506 @default.
- W2986543994 creator A5088379574 @default.
- W2986543994 date "2019-01-01" @default.
- W2986543994 modified "2023-09-24" @default.
- W2986543994 title "Learning to request guidance in emergent language" @default.
- W2986543994 cites W1525482321 @default.
- W2986543994 cites W2051228319 @default.
- W2986543994 cites W2129629813 @default.
- W2986543994 cites W218896052 @default.
- W2986543994 cites W2189089430 @default.
- W2986543994 cites W2242818861 @default.
- W2986543994 cites W2319920447 @default.
- W2986543994 cites W2416364697 @default.
- W2986543994 cites W2736601468 @default.
- W2986543994 cites W2760103357 @default.
- W2986543994 cites W2785955089 @default.
- W2986543994 cites W2790698955 @default.
- W2986543994 cites W2897513296 @default.
- W2986543994 cites W2901707424 @default.
- W2986543994 cites W2949992281 @default.
- W2986543994 cites W2950472486 @default.
- W2986543994 cites W2963026102 @default.
- W2986543994 cites W2963367022 @default.
- W2986543994 cites W2963367210 @default.
- W2986543994 cites W2963681240 @default.
- W2986543994 cites W2963717208 @default.
- W2986543994 cites W2963881016 @default.
- W2986543994 cites W2964217371 @default.
- W2986543994 cites W2964325826 @default.
- W2986543994 cites W2967186499 @default.
- W2986543994 cites W2967852106 @default.
- W2986543994 cites W3102103141 @default.
- W2986543994 doi "https://doi.org/10.18653/v1/d19-6407" @default.
- W2986543994 hasPublicationYear "2019" @default.
- W2986543994 type Work @default.
- W2986543994 sameAs 2986543994 @default.
- W2986543994 citedByCount "0" @default.
- W2986543994 crossrefType "proceedings-article" @default.
- W2986543994 hasAuthorship W2986543994A5007465102 @default.
- W2986543994 hasAuthorship W2986543994A5012032714 @default.
- W2986543994 hasAuthorship W2986543994A5013539443 @default.
- W2986543994 hasAuthorship W2986543994A5030844531 @default.
- W2986543994 hasAuthorship W2986543994A5041418006 @default.
- W2986543994 hasAuthorship W2986543994A5045425275 @default.
- W2986543994 hasAuthorship W2986543994A5052695225 @default.
- W2986543994 hasAuthorship W2986543994A5060248506 @default.
- W2986543994 hasAuthorship W2986543994A5088379574 @default.
- W2986543994 hasBestOaLocation W29865439941 @default.
- W2986543994 hasConcept C107457646 @default.
- W2986543994 hasConcept C126388530 @default.
- W2986543994 hasConcept C127162648 @default.
- W2986543994 hasConcept C127413603 @default.
- W2986543994 hasConcept C134306372 @default.
- W2986543994 hasConcept C136264566 @default.
- W2986543994 hasConcept C151201525 @default.
- W2986543994 hasConcept C154945302 @default.
- W2986543994 hasConcept C15744967 @default.
- W2986543994 hasConcept C162324750 @default.
- W2986543994 hasConcept C199360897 @default.
- W2986543994 hasConcept C201995342 @default.
- W2986543994 hasConcept C2775924081 @default.
- W2986543994 hasConcept C2780451532 @default.
- W2986543994 hasConcept C31258907 @default.
- W2986543994 hasConcept C33923547 @default.
- W2986543994 hasConcept C41008148 @default.
- W2986543994 hasConcept C77805123 @default.
- W2986543994 hasConcept C90329073 @default.
- W2986543994 hasConcept C98045186 @default.
- W2986543994 hasConceptScore W2986543994C107457646 @default.
- W2986543994 hasConceptScore W2986543994C126388530 @default.
- W2986543994 hasConceptScore W2986543994C127162648 @default.
- W2986543994 hasConceptScore W2986543994C127413603 @default.
- W2986543994 hasConceptScore W2986543994C134306372 @default.
- W2986543994 hasConceptScore W2986543994C136264566 @default.
- W2986543994 hasConceptScore W2986543994C151201525 @default.
- W2986543994 hasConceptScore W2986543994C154945302 @default.
- W2986543994 hasConceptScore W2986543994C15744967 @default.
- W2986543994 hasConceptScore W2986543994C162324750 @default.
- W2986543994 hasConceptScore W2986543994C199360897 @default.
- W2986543994 hasConceptScore W2986543994C201995342 @default.
- W2986543994 hasConceptScore W2986543994C2775924081 @default.
- W2986543994 hasConceptScore W2986543994C2780451532 @default.
- W2986543994 hasConceptScore W2986543994C31258907 @default.
- W2986543994 hasConceptScore W2986543994C33923547 @default.
- W2986543994 hasConceptScore W2986543994C41008148 @default.
- W2986543994 hasConceptScore W2986543994C77805123 @default.
- W2986543994 hasConceptScore W2986543994C90329073 @default.
- W2986543994 hasConceptScore W2986543994C98045186 @default.
- W2986543994 hasLocation W29865439941 @default.
- W2986543994 hasLocation W29865439942 @default.
- W2986543994 hasOpenAccess W2986543994 @default.