Matches in SemOpenAlex for { <https://semopenalex.org/work/W3030793591> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3030793591 endingPage "922" @default.
- W3030793591 startingPage "910" @default.
- W3030793591 abstract "Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding the most useful samples becomes critical in such settings. Existing approaches towards finding efficient exploration strategies add auxiliary objectives to promote exploration by the pre-update policy, however, this makes the adaptation using a few gradient steps difficult as the pre-update (exploration) and post-update (exploitation) policies are often quite different. Instead, we propose to explicitly model a separate exploration policy for the task distribution. Having two different policies gives more flexibility in training the exploration policy and also makes adaptation to any specific task easier. We show that using self-supervised or supervised learning objectives for adaptation allows for more efficient inner-loop updates and also demonstrate the superior performance of our model compared to prior works in this domain." @default.
- W3030793591 created "2020-06-05" @default.
- W3030793591 creator A5026667856 @default.
- W3030793591 creator A5063532655 @default.
- W3030793591 creator A5087505541 @default.
- W3030793591 date "2019-11-11" @default.
- W3030793591 modified "2023-09-26" @default.
- W3030793591 title "MAME : Model-Agnostic Meta-Exploration" @default.
- W3030793591 hasPublicationYear "2019" @default.
- W3030793591 type Work @default.
- W3030793591 sameAs 3030793591 @default.
- W3030793591 citedByCount "4" @default.
- W3030793591 countsByYear W30307935912020 @default.
- W3030793591 countsByYear W30307935912021 @default.
- W3030793591 crossrefType "journal-article" @default.
- W3030793591 hasAuthorship W3030793591A5026667856 @default.
- W3030793591 hasAuthorship W3030793591A5063532655 @default.
- W3030793591 hasAuthorship W3030793591A5087505541 @default.
- W3030793591 hasConcept C105795698 @default.
- W3030793591 hasConcept C119857082 @default.
- W3030793591 hasConcept C120665830 @default.
- W3030793591 hasConcept C121332964 @default.
- W3030793591 hasConcept C127413603 @default.
- W3030793591 hasConcept C134306372 @default.
- W3030793591 hasConcept C139807058 @default.
- W3030793591 hasConcept C154945302 @default.
- W3030793591 hasConcept C201995342 @default.
- W3030793591 hasConcept C2779436431 @default.
- W3030793591 hasConcept C2780451532 @default.
- W3030793591 hasConcept C2780598303 @default.
- W3030793591 hasConcept C2781002164 @default.
- W3030793591 hasConcept C33923547 @default.
- W3030793591 hasConcept C36503486 @default.
- W3030793591 hasConcept C41008148 @default.
- W3030793591 hasConcept C97541855 @default.
- W3030793591 hasConceptScore W3030793591C105795698 @default.
- W3030793591 hasConceptScore W3030793591C119857082 @default.
- W3030793591 hasConceptScore W3030793591C120665830 @default.
- W3030793591 hasConceptScore W3030793591C121332964 @default.
- W3030793591 hasConceptScore W3030793591C127413603 @default.
- W3030793591 hasConceptScore W3030793591C134306372 @default.
- W3030793591 hasConceptScore W3030793591C139807058 @default.
- W3030793591 hasConceptScore W3030793591C154945302 @default.
- W3030793591 hasConceptScore W3030793591C201995342 @default.
- W3030793591 hasConceptScore W3030793591C2779436431 @default.
- W3030793591 hasConceptScore W3030793591C2780451532 @default.
- W3030793591 hasConceptScore W3030793591C2780598303 @default.
- W3030793591 hasConceptScore W3030793591C2781002164 @default.
- W3030793591 hasConceptScore W3030793591C33923547 @default.
- W3030793591 hasConceptScore W3030793591C36503486 @default.
- W3030793591 hasConceptScore W3030793591C41008148 @default.
- W3030793591 hasConceptScore W3030793591C97541855 @default.
- W3030793591 hasLocation W30307935911 @default.
- W3030793591 hasOpenAccess W3030793591 @default.
- W3030793591 hasPrimaryLocation W30307935911 @default.
- W3030793591 hasRelatedWork W2800367501 @default.
- W3030793591 hasRelatedWork W2906917062 @default.
- W3030793591 hasRelatedWork W2907704766 @default.
- W3030793591 hasRelatedWork W2950722223 @default.
- W3030793591 hasRelatedWork W2952526277 @default.
- W3030793591 hasRelatedWork W2982795998 @default.
- W3030793591 hasRelatedWork W3005127431 @default.
- W3030793591 hasRelatedWork W3022124161 @default.
- W3030793591 hasRelatedWork W3035216917 @default.
- W3030793591 hasRelatedWork W3035689006 @default.
- W3030793591 hasRelatedWork W3037114224 @default.
- W3030793591 hasRelatedWork W3084024636 @default.
- W3030793591 hasRelatedWork W3092185126 @default.
- W3030793591 hasRelatedWork W3093147807 @default.
- W3030793591 hasRelatedWork W3095437761 @default.
- W3030793591 hasRelatedWork W3113994363 @default.
- W3030793591 hasRelatedWork W3126935522 @default.
- W3030793591 hasRelatedWork W3131310681 @default.
- W3030793591 hasRelatedWork W3195845308 @default.
- W3030793591 hasRelatedWork W778742492 @default.
- W3030793591 isParatext "false" @default.
- W3030793591 isRetracted "false" @default.
- W3030793591 magId "3030793591" @default.
- W3030793591 workType "article" @default.