Matches in SemOpenAlex for { <https://semopenalex.org/work/W2217025414> ?p ?o ?g. }
- W2217025414 endingPage "21" @default.
- W2217025414 startingPage "16" @default.
- W2217025414 abstract "Skill discovery algorithms in reinforcement learning typically identify single states or regions in state space that correspond to potential task-specific subgoals. However, such methods do not directly address the question of how many distinct skills are appropriate for solving the tasks that the agent faces. This can be highly inefficient when many identified subgoals correspond to the same underlying skill, but are all used individually as skill goals. Furthermore, skills created in this manner are often only transferable to tasks that share identical state spaces, since corresponding subgoals across tasks are not merged into a single skill goal. We show that these problems can be overcome by clustering subgoal data defined in an agent-space and using the resulting clusters as templates for skill termination conditions. Clustering via a Dirichlet process mixture model is used to discover a minimal, sufficient collection of portable skills." @default.
- W2217025414 created "2016-06-24" @default.
- W2217025414 creator A5043572737 @default.
- W2217025414 creator A5089808068 @default.
- W2217025414 date "2011-01-01" @default.
- W2217025414 modified "2023-09-24" @default.
- W2217025414 title "Clustering via Dirichlet process mixture models for portable skill discovery" @default.
- W2217025414 cites W1486707268 @default.
- W2217025414 cites W1492014007 @default.
- W2217025414 cites W1515851193 @default.
- W2217025414 cites W1540462738 @default.
- W2217025414 cites W1578521162 @default.
- W2217025414 cites W1586944634 @default.
- W2217025414 cites W1968768508 @default.
- W2217025414 cites W2080972498 @default.
- W2217025414 cites W2095951260 @default.
- W2217025414 cites W2100787464 @default.
- W2217025414 cites W2106261932 @default.
- W2217025414 cites W2108535023 @default.
- W2217025414 cites W2109910161 @default.
- W2217025414 cites W2114451917 @default.
- W2217025414 cites W2120636621 @default.
- W2217025414 cites W2143435603 @default.
- W2217025414 cites W2153668164 @default.
- W2217025414 cites W2165874743 @default.
- W2217025414 cites W2168640731 @default.
- W2217025414 cites W2204383650 @default.
- W2217025414 cites W2229272015 @default.
- W2217025414 cites W2104569262 @default.
- W2217025414 hasPublicationYear "2011" @default.
- W2217025414 type Work @default.
- W2217025414 sameAs 2217025414 @default.
- W2217025414 citedByCount "9" @default.
- W2217025414 countsByYear W22170254142013 @default.
- W2217025414 countsByYear W22170254142017 @default.
- W2217025414 countsByYear W22170254142018 @default.
- W2217025414 countsByYear W22170254142019 @default.
- W2217025414 countsByYear W22170254142020 @default.
- W2217025414 crossrefType "proceedings-article" @default.
- W2217025414 hasAuthorship W2217025414A5043572737 @default.
- W2217025414 hasAuthorship W2217025414A5089808068 @default.
- W2217025414 hasConcept C105795698 @default.
- W2217025414 hasConcept C111919701 @default.
- W2217025414 hasConcept C11413529 @default.
- W2217025414 hasConcept C119857082 @default.
- W2217025414 hasConcept C124101348 @default.
- W2217025414 hasConcept C127413603 @default.
- W2217025414 hasConcept C134306372 @default.
- W2217025414 hasConcept C154945302 @default.
- W2217025414 hasConcept C169214877 @default.
- W2217025414 hasConcept C182310444 @default.
- W2217025414 hasConcept C201995342 @default.
- W2217025414 hasConcept C2778572836 @default.
- W2217025414 hasConcept C2780451532 @default.
- W2217025414 hasConcept C33923547 @default.
- W2217025414 hasConcept C41008148 @default.
- W2217025414 hasConcept C48103436 @default.
- W2217025414 hasConcept C72434380 @default.
- W2217025414 hasConcept C73555534 @default.
- W2217025414 hasConcept C97541855 @default.
- W2217025414 hasConcept C98045186 @default.
- W2217025414 hasConceptScore W2217025414C105795698 @default.
- W2217025414 hasConceptScore W2217025414C111919701 @default.
- W2217025414 hasConceptScore W2217025414C11413529 @default.
- W2217025414 hasConceptScore W2217025414C119857082 @default.
- W2217025414 hasConceptScore W2217025414C124101348 @default.
- W2217025414 hasConceptScore W2217025414C127413603 @default.
- W2217025414 hasConceptScore W2217025414C134306372 @default.
- W2217025414 hasConceptScore W2217025414C154945302 @default.
- W2217025414 hasConceptScore W2217025414C169214877 @default.
- W2217025414 hasConceptScore W2217025414C182310444 @default.
- W2217025414 hasConceptScore W2217025414C201995342 @default.
- W2217025414 hasConceptScore W2217025414C2778572836 @default.
- W2217025414 hasConceptScore W2217025414C2780451532 @default.
- W2217025414 hasConceptScore W2217025414C33923547 @default.
- W2217025414 hasConceptScore W2217025414C41008148 @default.
- W2217025414 hasConceptScore W2217025414C48103436 @default.
- W2217025414 hasConceptScore W2217025414C72434380 @default.
- W2217025414 hasConceptScore W2217025414C73555534 @default.
- W2217025414 hasConceptScore W2217025414C97541855 @default.
- W2217025414 hasConceptScore W2217025414C98045186 @default.
- W2217025414 hasLocation W22170254141 @default.
- W2217025414 hasOpenAccess W2217025414 @default.
- W2217025414 hasPrimaryLocation W22170254141 @default.
- W2217025414 hasRelatedWork W1603565927 @default.
- W2217025414 hasRelatedWork W2056884876 @default.
- W2217025414 hasRelatedWork W2108535023 @default.
- W2217025414 hasRelatedWork W2109910161 @default.
- W2217025414 hasRelatedWork W2127031267 @default.
- W2217025414 hasRelatedWork W2165300526 @default.
- W2217025414 hasRelatedWork W2211996086 @default.
- W2217025414 hasRelatedWork W2523124567 @default.
- W2217025414 hasRelatedWork W2741995169 @default.
- W2217025414 hasRelatedWork W2768663371 @default.
- W2217025414 hasRelatedWork W2775536965 @default.
- W2217025414 hasRelatedWork W2788519588 @default.
- W2217025414 hasRelatedWork W2952897246 @default.
- W2217025414 hasRelatedWork W2964505566 @default.