Matches in SemOpenAlex for { <https://semopenalex.org/work/W2106008664> ?p ?o ?g. }
- W2106008664 endingPage "1214" @default.
- W2106008664 startingPage "1206" @default.
- W2106008664 abstract "Policy gradient algorithms have shown considerable recent success in solving high-dimensional sequential decision making tasks, particularly in robotics. However, these methods often require extensive experience in a domain to achieve high performance. To make agents more sample-efficient, we developed a multi-task policy gradient method to learn decision making tasks consecutively, transferring knowledge between tasks to accelerate learning. Our approach provides robust theoretical guarantees, and we show empirically that it dramatically accelerates learning on a variety of dynamical systems, including an application to quadrotor control." @default.
- W2106008664 created "2016-06-24" @default.
- W2106008664 creator A5005962804 @default.
- W2106008664 creator A5020691490 @default.
- W2106008664 creator A5034334762 @default.
- W2106008664 creator A5070914351 @default.
- W2106008664 date "2014-06-21" @default.
- W2106008664 modified "2023-09-23" @default.
- W2106008664 title "Online Multi-Task Learning for Policy Gradient Methods" @default.
- W2106008664 cites W110451278 @default.
- W2106008664 cites W1519626139 @default.
- W2106008664 cites W1533535072 @default.
- W2106008664 cites W1560550898 @default.
- W2106008664 cites W1626155273 @default.
- W2106008664 cites W1929309940 @default.
- W2106008664 cites W1942758450 @default.
- W2106008664 cites W1969074599 @default.
- W2106008664 cites W1974043469 @default.
- W2106008664 cites W2012392077 @default.
- W2106008664 cites W204815387 @default.
- W2106008664 cites W2084549025 @default.
- W2106008664 cites W2088038240 @default.
- W2106008664 cites W2091714857 @default.
- W2106008664 cites W2097381042 @default.
- W2106008664 cites W2098723043 @default.
- W2106008664 cites W2114235770 @default.
- W2106008664 cites W2119007372 @default.
- W2106008664 cites W2119717200 @default.
- W2106008664 cites W2134197408 @default.
- W2106008664 cites W2154328025 @default.
- W2106008664 cites W2155027007 @default.
- W2106008664 cites W2158150115 @default.
- W2106008664 cites W2158760659 @default.
- W2106008664 cites W2169743339 @default.
- W2106008664 cites W2172968643 @default.
- W2106008664 cites W2963424430 @default.
- W2106008664 hasPublicationYear "2014" @default.
- W2106008664 type Work @default.
- W2106008664 sameAs 2106008664 @default.
- W2106008664 citedByCount "67" @default.
- W2106008664 countsByYear W21060086642014 @default.
- W2106008664 countsByYear W21060086642015 @default.
- W2106008664 countsByYear W21060086642016 @default.
- W2106008664 countsByYear W21060086642017 @default.
- W2106008664 countsByYear W21060086642018 @default.
- W2106008664 countsByYear W21060086642019 @default.
- W2106008664 countsByYear W21060086642020 @default.
- W2106008664 countsByYear W21060086642021 @default.
- W2106008664 countsByYear W21060086642022 @default.
- W2106008664 crossrefType "proceedings-article" @default.
- W2106008664 hasAuthorship W2106008664A5005962804 @default.
- W2106008664 hasAuthorship W2106008664A5020691490 @default.
- W2106008664 hasAuthorship W2106008664A5034334762 @default.
- W2106008664 hasAuthorship W2106008664A5070914351 @default.
- W2106008664 hasConcept C119857082 @default.
- W2106008664 hasConcept C127413603 @default.
- W2106008664 hasConcept C134306372 @default.
- W2106008664 hasConcept C136197465 @default.
- W2106008664 hasConcept C154945302 @default.
- W2106008664 hasConcept C185592680 @default.
- W2106008664 hasConcept C198531522 @default.
- W2106008664 hasConcept C201995342 @default.
- W2106008664 hasConcept C207685749 @default.
- W2106008664 hasConcept C2780451532 @default.
- W2106008664 hasConcept C33923547 @default.
- W2106008664 hasConcept C34413123 @default.
- W2106008664 hasConcept C36503486 @default.
- W2106008664 hasConcept C41008148 @default.
- W2106008664 hasConcept C43617362 @default.
- W2106008664 hasConcept C90509273 @default.
- W2106008664 hasConcept C97541855 @default.
- W2106008664 hasConceptScore W2106008664C119857082 @default.
- W2106008664 hasConceptScore W2106008664C127413603 @default.
- W2106008664 hasConceptScore W2106008664C134306372 @default.
- W2106008664 hasConceptScore W2106008664C136197465 @default.
- W2106008664 hasConceptScore W2106008664C154945302 @default.
- W2106008664 hasConceptScore W2106008664C185592680 @default.
- W2106008664 hasConceptScore W2106008664C198531522 @default.
- W2106008664 hasConceptScore W2106008664C201995342 @default.
- W2106008664 hasConceptScore W2106008664C207685749 @default.
- W2106008664 hasConceptScore W2106008664C2780451532 @default.
- W2106008664 hasConceptScore W2106008664C33923547 @default.
- W2106008664 hasConceptScore W2106008664C34413123 @default.
- W2106008664 hasConceptScore W2106008664C36503486 @default.
- W2106008664 hasConceptScore W2106008664C41008148 @default.
- W2106008664 hasConceptScore W2106008664C43617362 @default.
- W2106008664 hasConceptScore W2106008664C90509273 @default.
- W2106008664 hasConceptScore W2106008664C97541855 @default.
- W2106008664 hasLocation W21060086641 @default.
- W2106008664 hasOpenAccess W2106008664 @default.
- W2106008664 hasPrimaryLocation W21060086641 @default.
- W2106008664 hasRelatedWork W1492014007 @default.
- W2106008664 hasRelatedWork W1519626139 @default.
- W2106008664 hasRelatedWork W1560550898 @default.
- W2106008664 hasRelatedWork W158722652 @default.
- W2106008664 hasRelatedWork W1757796397 @default.
- W2106008664 hasRelatedWork W1848094219 @default.
- W2106008664 hasRelatedWork W2004030284 @default.