FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2735519198> ?p ?o ?g. }

• W2735519198 abstract "Policy gradient algorithms are useful reinforcement learning methods which optimize a control policy by performing stochastic gradient descent with respect to controller parameters. In this paper, we extend actor-critic algorithms by adding an l 1 norm regularization on the actor part, which makes our algorithm automatically select and optimize the useful controller basis functions. Our method is closely related to existing approaches to sparse controller design and actuator selection, but in contrast to these, our approach runs online and does not require a plant model. In order to utilize l 1 regularization online, the actor updates are extended to include an iterative soft-thresholding step. Convergence of the algorithm is proved using methods from stochastic approximation. The effectiveness of our algorithm for control basis and actuator selection is demonstrated on numerical examples." @default.
• W2735519198 created "2017-07-21" @default.
• W2735519198 creator A5024915129 @default.
• W2735519198 creator A5033424858 @default.
• W2735519198 date "2017-05-01" @default.
• W2735519198 modified "2023-09-25" @default.
• W2735519198 title "Online control basis selection by a regularized actor critic algorithm" @default.
• W2735519198 cites W1597303641 @default.
• W2735519198 cites W1616818660 @default.
• W2735519198 cites W1981657694 @default.
• W2735519198 cites W2009303086 @default.
• W2735519198 cites W2013943064 @default.
• W2735519198 cites W2028781966 @default.
• W2735519198 cites W2050834445 @default.
• W2735519198 cites W2058590322 @default.
• W2735519198 cites W2076562540 @default.
• W2735519198 cites W2082261506 @default.
• W2735519198 cites W2094387729 @default.
• W2735519198 cites W2107726111 @default.
• W2735519198 cites W2108682071 @default.
• W2735519198 cites W2112264645 @default.
• W2735519198 cites W2114537044 @default.
• W2735519198 cites W2115706991 @default.
• W2735519198 cites W2119717200 @default.
• W2735519198 cites W2129638195 @default.
• W2735519198 cites W2138019504 @default.
• W2735519198 cites W2139418546 @default.
• W2735519198 cites W2155027007 @default.
• W2735519198 cites W2156737235 @default.
• W2735519198 cites W2169207653 @default.
• W2735519198 cites W2173945562 @default.
• W2735519198 cites W2964326866 @default.
• W2735519198 cites W3102961917 @default.
• W2735519198 cites W32403112 @default.
• W2735519198 doi "https://doi.org/10.23919/acc.2017.7963640" @default.
• W2735519198 hasPublicationYear "2017" @default.
• W2735519198 type Work @default.
• W2735519198 sameAs 2735519198 @default.
• W2735519198 citedByCount "3" @default.
• W2735519198 countsByYear W27355191982018 @default.
• W2735519198 countsByYear W27355191982019 @default.
• W2735519198 countsByYear W27355191982020 @default.
• W2735519198 crossrefType "proceedings-article" @default.
• W2735519198 hasAuthorship W2735519198A5024915129 @default.
• W2735519198 hasAuthorship W2735519198A5033424858 @default.
• W2735519198 hasConcept C11413529 @default.
• W2735519198 hasConcept C115961682 @default.
• W2735519198 hasConcept C12426560 @default.
• W2735519198 hasConcept C126255220 @default.
• W2735519198 hasConcept C154945302 @default.
• W2735519198 hasConcept C191178318 @default.
• W2735519198 hasConcept C203479927 @default.
• W2735519198 hasConcept C2524010 @default.
• W2735519198 hasConcept C2776135515 @default.
• W2735519198 hasConcept C33923547 @default.
• W2735519198 hasConcept C41008148 @default.
• W2735519198 hasConcept C6557445 @default.
• W2735519198 hasConcept C81917197 @default.
• W2735519198 hasConcept C86803240 @default.
• W2735519198 hasConcept C97541855 @default.
• W2735519198 hasConceptScore W2735519198C11413529 @default.
• W2735519198 hasConceptScore W2735519198C115961682 @default.
• W2735519198 hasConceptScore W2735519198C12426560 @default.
• W2735519198 hasConceptScore W2735519198C126255220 @default.
• W2735519198 hasConceptScore W2735519198C154945302 @default.
• W2735519198 hasConceptScore W2735519198C191178318 @default.
• W2735519198 hasConceptScore W2735519198C203479927 @default.
• W2735519198 hasConceptScore W2735519198C2524010 @default.
• W2735519198 hasConceptScore W2735519198C2776135515 @default.
• W2735519198 hasConceptScore W2735519198C33923547 @default.
• W2735519198 hasConceptScore W2735519198C41008148 @default.
• W2735519198 hasConceptScore W2735519198C6557445 @default.
• W2735519198 hasConceptScore W2735519198C81917197 @default.
• W2735519198 hasConceptScore W2735519198C86803240 @default.
• W2735519198 hasConceptScore W2735519198C97541855 @default.
• W2735519198 hasLocation W27355191981 @default.
• W2735519198 hasOpenAccess W2735519198 @default.
• W2735519198 hasPrimaryLocation W27355191981 @default.
• W2735519198 hasRelatedWork W1591368059 @default.
• W2735519198 hasRelatedWork W1975730686 @default.
• W2735519198 hasRelatedWork W1989015519 @default.
• W2735519198 hasRelatedWork W2001503211 @default.
• W2735519198 hasRelatedWork W2012173089 @default.
• W2735519198 hasRelatedWork W2161307520 @default.
• W2735519198 hasRelatedWork W2164906629 @default.
• W2735519198 hasRelatedWork W2290631086 @default.
• W2735519198 hasRelatedWork W2354965734 @default.
• W2735519198 hasRelatedWork W2560552350 @default.
• W2735519198 hasRelatedWork W2610160698 @default.
• W2735519198 hasRelatedWork W2895139421 @default.
• W2735519198 hasRelatedWork W2914426538 @default.
• W2735519198 hasRelatedWork W2963720943 @default.
• W2735519198 hasRelatedWork W2963801017 @default.
• W2735519198 hasRelatedWork W2999245049 @default.
• W2735519198 hasRelatedWork W3008382482 @default.
• W2735519198 hasRelatedWork W3010406211 @default.
• W2735519198 hasRelatedWork W3011877502 @default.
• W2735519198 hasRelatedWork W3112047150 @default.
• W2735519198 isParatext "false" @default.
• W2735519198 isRetracted "false" @default.

• next