FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2104733512> ?p ?o ?g. }

• W2104733512 endingPage "9" @default.
• W2104733512 startingPage "1" @default.
• W2104733512 abstract "Direct policy search can effectively scale to high-dimensional systems, but complex policies with hundreds of parameters often present a challenge for such methods, requiring numerous samples and often falling into poor local optima. We present a guided policy search algorithm that uses trajectory optimization to direct policy learning and avoid poor local optima. We show how differential dynamic programming can be used to generate suitable guiding samples, and describe a regularized importance sampled policy optimization that incorporates these samples into the policy search. We evaluate the method by learning neural network controllers for planar swimming, hopping, and walking, as well as simulated 3D humanoid running." @default.
• W2104733512 created "2016-06-24" @default.
• W2104733512 creator A5006181255 @default.
• W2104733512 creator A5026322200 @default.
• W2104733512 date "2013-06-16" @default.
• W2104733512 modified "2023-10-02" @default.
• W2104733512 title "Guided Policy Search" @default.
• W2104733512 cites W1559990548 @default.
• W2104733512 cites W1575592356 @default.
• W2104733512 cites W1814308503 @default.
• W2104733512 cites W2001165022 @default.
• W2104733512 cites W2019965290 @default.
• W2104733512 cites W2087617385 @default.
• W2104733512 cites W2109008048 @default.
• W2104733512 cites W2110304639 @default.
• W2104733512 cites W2125612430 @default.
• W2104733512 cites W2127027287 @default.
• W2104733512 cites W2130094217 @default.
• W2104733512 cites W2138839127 @default.
• W2104733512 cites W2140135625 @default.
• W2104733512 cites W2155027007 @default.
• W2104733512 cites W2158782408 @default.
• W2104733512 cites W2158796564 @default.
• W2104733512 cites W2161872510 @default.
• W2104733512 cites W2162262334 @default.
• W2104733512 cites W2165421048 @default.
• W2104733512 cites W2169209873 @default.
• W2104733512 cites W2253356247 @default.
• W2104733512 cites W2962957031 @default.
• W2104733512 cites W2964349150 @default.
• W2104733512 cites W64088143 @default.
• W2104733512 hasPublicationYear "2013" @default.
• W2104733512 type Work @default.
• W2104733512 sameAs 2104733512 @default.
• W2104733512 citedByCount "350" @default.
• W2104733512 countsByYear W21047335122013 @default.
• W2104733512 countsByYear W21047335122014 @default.
• W2104733512 countsByYear W21047335122015 @default.
• W2104733512 countsByYear W21047335122016 @default.
• W2104733512 countsByYear W21047335122017 @default.
• W2104733512 countsByYear W21047335122018 @default.
• W2104733512 countsByYear W21047335122019 @default.
• W2104733512 countsByYear W21047335122020 @default.
• W2104733512 countsByYear W21047335122021 @default.
• W2104733512 countsByYear W21047335122022 @default.
• W2104733512 countsByYear W21047335122023 @default.
• W2104733512 crossrefType "proceedings-article" @default.
• W2104733512 hasAuthorship W2104733512A5006181255 @default.
• W2104733512 hasAuthorship W2104733512A5026322200 @default.
• W2104733512 hasConcept C11413529 @default.
• W2104733512 hasConcept C119857082 @default.
• W2104733512 hasConcept C121332964 @default.
• W2104733512 hasConcept C126255220 @default.
• W2104733512 hasConcept C1276947 @default.
• W2104733512 hasConcept C13662910 @default.
• W2104733512 hasConcept C141934464 @default.
• W2104733512 hasConcept C154945302 @default.
• W2104733512 hasConcept C173246807 @default.
• W2104733512 hasConcept C33923547 @default.
• W2104733512 hasConcept C37404715 @default.
• W2104733512 hasConcept C41008148 @default.
• W2104733512 hasConcept C50644808 @default.
• W2104733512 hasConcept C91575142 @default.
• W2104733512 hasConcept C92292787 @default.
• W2104733512 hasConcept C97541855 @default.
• W2104733512 hasConceptScore W2104733512C11413529 @default.
• W2104733512 hasConceptScore W2104733512C119857082 @default.
• W2104733512 hasConceptScore W2104733512C121332964 @default.
• W2104733512 hasConceptScore W2104733512C126255220 @default.
• W2104733512 hasConceptScore W2104733512C1276947 @default.
• W2104733512 hasConceptScore W2104733512C13662910 @default.
• W2104733512 hasConceptScore W2104733512C141934464 @default.
• W2104733512 hasConceptScore W2104733512C154945302 @default.
• W2104733512 hasConceptScore W2104733512C173246807 @default.
• W2104733512 hasConceptScore W2104733512C33923547 @default.
• W2104733512 hasConceptScore W2104733512C37404715 @default.
• W2104733512 hasConceptScore W2104733512C41008148 @default.
• W2104733512 hasConceptScore W2104733512C50644808 @default.
• W2104733512 hasConceptScore W2104733512C91575142 @default.
• W2104733512 hasConceptScore W2104733512C92292787 @default.
• W2104733512 hasConceptScore W2104733512C97541855 @default.
• W2104733512 hasLocation W21047335121 @default.
• W2104733512 hasOpenAccess W2104733512 @default.
• W2104733512 hasPrimaryLocation W21047335121 @default.
• W2104733512 hasRelatedWork W1757796397 @default.
• W2104733512 hasRelatedWork W1771410628 @default.
• W2104733512 hasRelatedWork W1977655452 @default.
• W2104733512 hasRelatedWork W2012587148 @default.
• W2104733512 hasRelatedWork W2087617385 @default.
• W2104733512 hasRelatedWork W2119717200 @default.
• W2104733512 hasRelatedWork W2121103318 @default.
• W2104733512 hasRelatedWork W2121863487 @default.
• W2104733512 hasRelatedWork W2140135625 @default.
• W2104733512 hasRelatedWork W2145339207 @default.
• W2104733512 hasRelatedWork W2155027007 @default.
• W2104733512 hasRelatedWork W2158782408 @default.
• W2104733512 hasRelatedWork W2165150801 @default.
• W2104733512 hasRelatedWork W2173248099 @default.

• next