Matches in SemOpenAlex for { <https://semopenalex.org/work/W4303411701> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4303411701 abstract "This paper studies the adaptive optimal stationary control of continuous-time linear stochastic systems with both additive and multiplicative noises, using reinforcement learning techniques. Based on policy iteration, a novel off-policy reinforcement learning algorithm, named optimistic least-squares-based policy iteration, is proposed which is able to find iteratively near-optimal policies of the adaptive optimal stationary control problem directly from input/state data without explicitly identifying any system matrices, starting from an initial admissible control policy. The solutions given by the proposed optimistic least-squares-based policy iteration are proved to converge to a small neighborhood of the optimal solution with probability one, under mild conditions. The application of the proposed algorithm to a triple inverted pendulum example validates its feasibility and effectiveness." @default.
- W4303411701 created "2022-10-07" @default.
- W4303411701 creator A5058655480 @default.
- W4303411701 creator A5067046312 @default.
- W4303411701 date "2021-07-16" @default.
- W4303411701 modified "2023-09-24" @default.
- W4303411701 title "Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems" @default.
- W4303411701 doi "https://doi.org/10.48550/arxiv.2107.07788" @default.
- W4303411701 hasPublicationYear "2021" @default.
- W4303411701 type Work @default.
- W4303411701 citedByCount "0" @default.
- W4303411701 crossrefType "posted-content" @default.
- W4303411701 hasAuthorship W4303411701A5058655480 @default.
- W4303411701 hasAuthorship W4303411701A5067046312 @default.
- W4303411701 hasBestOaLocation W43034117011 @default.
- W4303411701 hasConcept C105795698 @default.
- W4303411701 hasConcept C106189395 @default.
- W4303411701 hasConcept C107464732 @default.
- W4303411701 hasConcept C11413529 @default.
- W4303411701 hasConcept C121332964 @default.
- W4303411701 hasConcept C126255220 @default.
- W4303411701 hasConcept C131021393 @default.
- W4303411701 hasConcept C13412647 @default.
- W4303411701 hasConcept C134306372 @default.
- W4303411701 hasConcept C154945302 @default.
- W4303411701 hasConcept C158622935 @default.
- W4303411701 hasConcept C159886148 @default.
- W4303411701 hasConcept C170131372 @default.
- W4303411701 hasConcept C18015164 @default.
- W4303411701 hasConcept C192921069 @default.
- W4303411701 hasConcept C2775924081 @default.
- W4303411701 hasConcept C33923547 @default.
- W4303411701 hasConcept C41008148 @default.
- W4303411701 hasConcept C42747912 @default.
- W4303411701 hasConcept C47446073 @default.
- W4303411701 hasConcept C48103436 @default.
- W4303411701 hasConcept C62520636 @default.
- W4303411701 hasConcept C84462506 @default.
- W4303411701 hasConcept C91575142 @default.
- W4303411701 hasConcept C9390403 @default.
- W4303411701 hasConcept C97541855 @default.
- W4303411701 hasConceptScore W4303411701C105795698 @default.
- W4303411701 hasConceptScore W4303411701C106189395 @default.
- W4303411701 hasConceptScore W4303411701C107464732 @default.
- W4303411701 hasConceptScore W4303411701C11413529 @default.
- W4303411701 hasConceptScore W4303411701C121332964 @default.
- W4303411701 hasConceptScore W4303411701C126255220 @default.
- W4303411701 hasConceptScore W4303411701C131021393 @default.
- W4303411701 hasConceptScore W4303411701C13412647 @default.
- W4303411701 hasConceptScore W4303411701C134306372 @default.
- W4303411701 hasConceptScore W4303411701C154945302 @default.
- W4303411701 hasConceptScore W4303411701C158622935 @default.
- W4303411701 hasConceptScore W4303411701C159886148 @default.
- W4303411701 hasConceptScore W4303411701C170131372 @default.
- W4303411701 hasConceptScore W4303411701C18015164 @default.
- W4303411701 hasConceptScore W4303411701C192921069 @default.
- W4303411701 hasConceptScore W4303411701C2775924081 @default.
- W4303411701 hasConceptScore W4303411701C33923547 @default.
- W4303411701 hasConceptScore W4303411701C41008148 @default.
- W4303411701 hasConceptScore W4303411701C42747912 @default.
- W4303411701 hasConceptScore W4303411701C47446073 @default.
- W4303411701 hasConceptScore W4303411701C48103436 @default.
- W4303411701 hasConceptScore W4303411701C62520636 @default.
- W4303411701 hasConceptScore W4303411701C84462506 @default.
- W4303411701 hasConceptScore W4303411701C91575142 @default.
- W4303411701 hasConceptScore W4303411701C9390403 @default.
- W4303411701 hasConceptScore W4303411701C97541855 @default.
- W4303411701 hasLocation W43034117011 @default.
- W4303411701 hasOpenAccess W4303411701 @default.
- W4303411701 hasPrimaryLocation W43034117011 @default.
- W4303411701 hasRelatedWork W2050140468 @default.
- W4303411701 hasRelatedWork W2993197237 @default.
- W4303411701 hasRelatedWork W3181585847 @default.
- W4303411701 hasRelatedWork W3184481401 @default.
- W4303411701 hasRelatedWork W4285128439 @default.
- W4303411701 hasRelatedWork W4287997525 @default.
- W4303411701 hasRelatedWork W4303411701 @default.
- W4303411701 hasRelatedWork W4308505035 @default.
- W4303411701 hasRelatedWork W2400643431 @default.
- W4303411701 hasRelatedWork W3110455746 @default.
- W4303411701 isParatext "false" @default.
- W4303411701 isRetracted "false" @default.
- W4303411701 workType "article" @default.