Matches in SemOpenAlex for { <https://semopenalex.org/work/W2337330> ?p ?o ?g. }
- W2337330 endingPage "762" @default.
- W2337330 startingPage "756" @default.
- W2337330 abstract "Imitation learning, also called learning by watching or programming by demonstration, has emerged as a means of accelerating many reinforcement learning tasks. Previous work has shown the value of imitation in domains where a single mentor demonstrates execution of a known optimal policy for the benefit of a learning agent. We consider the more general scenario of learning from mentors who are themselves agents seeking to maximize their own rewards. We propose a new algorithm based on the concept of transferable utility for ensuring that an observer agent can learn efficiently in the context of a selfish, not necessarily helpful, mentor. We also address the questions of when an imitative agent should request help from a mentor, and when the mentor can be expected to acknowledge a request for help. In analogy with other types of active learning, we call the proposed approach active imitation learning." @default.
- W2337330 created "2016-06-24" @default.
- W2337330 creator A5002759219 @default.
- W2337330 creator A5015174186 @default.
- W2337330 creator A5020306781 @default.
- W2337330 date "2007-07-22" @default.
- W2337330 modified "2023-09-24" @default.
- W2337330 title "Active imitation learning" @default.
- W2337330 cites W1496855202 @default.
- W2337330 cites W1521332421 @default.
- W2337330 cites W1533301287 @default.
- W2337330 cites W1549584663 @default.
- W2337330 cites W1591803298 @default.
- W2337330 cites W1594602740 @default.
- W2337330 cites W1999874108 @default.
- W2337330 cites W2001863269 @default.
- W2337330 cites W2062663664 @default.
- W2337330 cites W2105754823 @default.
- W2337330 cites W2148112459 @default.
- W2337330 cites W2159951376 @default.
- W2337330 cites W2587628976 @default.
- W2337330 cites W3150555252 @default.
- W2337330 hasPublicationYear "2007" @default.
- W2337330 type Work @default.
- W2337330 sameAs 2337330 @default.
- W2337330 citedByCount "12" @default.
- W2337330 countsByYear W23373302012 @default.
- W2337330 countsByYear W23373302013 @default.
- W2337330 countsByYear W23373302014 @default.
- W2337330 countsByYear W23373302015 @default.
- W2337330 countsByYear W23373302017 @default.
- W2337330 countsByYear W23373302019 @default.
- W2337330 crossrefType "proceedings-article" @default.
- W2337330 hasAuthorship W2337330A5002759219 @default.
- W2337330 hasAuthorship W2337330A5015174186 @default.
- W2337330 hasAuthorship W2337330A5020306781 @default.
- W2337330 hasConcept C107457646 @default.
- W2337330 hasConcept C119857082 @default.
- W2337330 hasConcept C12298181 @default.
- W2337330 hasConcept C126388530 @default.
- W2337330 hasConcept C138885662 @default.
- W2337330 hasConcept C151730666 @default.
- W2337330 hasConcept C154945302 @default.
- W2337330 hasConcept C15744967 @default.
- W2337330 hasConcept C188888258 @default.
- W2337330 hasConcept C19966478 @default.
- W2337330 hasConcept C2776291640 @default.
- W2337330 hasConcept C2779343474 @default.
- W2337330 hasConcept C34868163 @default.
- W2337330 hasConcept C41008148 @default.
- W2337330 hasConcept C41895202 @default.
- W2337330 hasConcept C521332185 @default.
- W2337330 hasConcept C77805123 @default.
- W2337330 hasConcept C77967617 @default.
- W2337330 hasConcept C86803240 @default.
- W2337330 hasConcept C90509273 @default.
- W2337330 hasConcept C97541855 @default.
- W2337330 hasConceptScore W2337330C107457646 @default.
- W2337330 hasConceptScore W2337330C119857082 @default.
- W2337330 hasConceptScore W2337330C12298181 @default.
- W2337330 hasConceptScore W2337330C126388530 @default.
- W2337330 hasConceptScore W2337330C138885662 @default.
- W2337330 hasConceptScore W2337330C151730666 @default.
- W2337330 hasConceptScore W2337330C154945302 @default.
- W2337330 hasConceptScore W2337330C15744967 @default.
- W2337330 hasConceptScore W2337330C188888258 @default.
- W2337330 hasConceptScore W2337330C19966478 @default.
- W2337330 hasConceptScore W2337330C2776291640 @default.
- W2337330 hasConceptScore W2337330C2779343474 @default.
- W2337330 hasConceptScore W2337330C34868163 @default.
- W2337330 hasConceptScore W2337330C41008148 @default.
- W2337330 hasConceptScore W2337330C41895202 @default.
- W2337330 hasConceptScore W2337330C521332185 @default.
- W2337330 hasConceptScore W2337330C77805123 @default.
- W2337330 hasConceptScore W2337330C77967617 @default.
- W2337330 hasConceptScore W2337330C86803240 @default.
- W2337330 hasConceptScore W2337330C90509273 @default.
- W2337330 hasConceptScore W2337330C97541855 @default.
- W2337330 hasLocation W23373301 @default.
- W2337330 hasOpenAccess W2337330 @default.
- W2337330 hasPrimaryLocation W23373301 @default.
- W2337330 hasRelatedWork W1521687449 @default.
- W2337330 hasRelatedWork W1539975474 @default.
- W2337330 hasRelatedWork W1540685400 @default.
- W2337330 hasRelatedWork W1684361744 @default.
- W2337330 hasRelatedWork W1971890413 @default.
- W2337330 hasRelatedWork W1986014385 @default.
- W2337330 hasRelatedWork W1999874108 @default.
- W2337330 hasRelatedWork W2004303440 @default.
- W2337330 hasRelatedWork W2061562262 @default.
- W2337330 hasRelatedWork W2070678636 @default.
- W2337330 hasRelatedWork W2097113539 @default.
- W2337330 hasRelatedWork W2118710279 @default.
- W2337330 hasRelatedWork W2119388568 @default.
- W2337330 hasRelatedWork W2121863487 @default.
- W2337330 hasRelatedWork W2135681007 @default.
- W2337330 hasRelatedWork W2154018708 @default.
- W2337330 hasRelatedWork W2156163138 @default.