Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315488852> ?p ?o ?g. }
- W4315488852 abstract "The convergence of policy gradient algorithms in reinforcement learning hinges on the optimization landscape of the underlying optimal control problem. Theoretical insights into these algorithms can often be acquired from analyzing those of linear quadratic control. However, most of the existing literature only considers the optimization landscape for static full-state or output feedback policies (controllers). We investigate the more challenging case of dynamic output-feedback policies for linear quadratic regulation (abbreviated as dLQR), which is prevalent in practice but has a rather complicated optimization landscape. We first show how the dLQR cost varies with the coordinate transformation of the dynamic controller and then derive the optimal transformation for a given observable stabilizing controller. At the core of our results is the uniqueness of the stationary point of dLQR when it is observable, which is in a concise form of an observer-based controller with the optimal similarity transformation. These results shed light on designing efficient algorithms for general decision-making problems with partially observed information." @default.
- W4315488852 created "2023-01-11" @default.
- W4315488852 creator A5007347795 @default.
- W4315488852 creator A5042517380 @default.
- W4315488852 creator A5067909017 @default.
- W4315488852 creator A5085369108 @default.
- W4315488852 date "2022-12-06" @default.
- W4315488852 modified "2023-10-18" @default.
- W4315488852 title "On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator" @default.
- W4315488852 cites W2145339207 @default.
- W4315488852 cites W2161367843 @default.
- W4315488852 cites W2180470641 @default.
- W4315488852 cites W2484646121 @default.
- W4315488852 cites W2523345745 @default.
- W4315488852 cites W2807176303 @default.
- W4315488852 cites W2903410452 @default.
- W4315488852 cites W2907944110 @default.
- W4315488852 cites W2930863966 @default.
- W4315488852 cites W2963842088 @default.
- W4315488852 cites W2999535065 @default.
- W4315488852 cites W3011908139 @default.
- W4315488852 cites W3087319130 @default.
- W4315488852 cites W3087896133 @default.
- W4315488852 cites W3158594576 @default.
- W4315488852 cites W3185181536 @default.
- W4315488852 cites W3206480318 @default.
- W4315488852 cites W4210317951 @default.
- W4315488852 cites W4213377513 @default.
- W4315488852 cites W4294692180 @default.
- W4315488852 doi "https://doi.org/10.1109/cdc51059.2022.9992503" @default.
- W4315488852 hasPublicationYear "2022" @default.
- W4315488852 type Work @default.
- W4315488852 citedByCount "2" @default.
- W4315488852 countsByYear W43154888522023 @default.
- W4315488852 crossrefType "proceedings-article" @default.
- W4315488852 hasAuthorship W4315488852A5007347795 @default.
- W4315488852 hasAuthorship W4315488852A5042517380 @default.
- W4315488852 hasAuthorship W4315488852A5067909017 @default.
- W4315488852 hasAuthorship W4315488852A5085369108 @default.
- W4315488852 hasBestOaLocation W43154888522 @default.
- W4315488852 hasConcept C104317684 @default.
- W4315488852 hasConcept C121332964 @default.
- W4315488852 hasConcept C126255220 @default.
- W4315488852 hasConcept C134306372 @default.
- W4315488852 hasConcept C137836250 @default.
- W4315488852 hasConcept C154945302 @default.
- W4315488852 hasConcept C162324750 @default.
- W4315488852 hasConcept C185592680 @default.
- W4315488852 hasConcept C203479927 @default.
- W4315488852 hasConcept C204241405 @default.
- W4315488852 hasConcept C204495892 @default.
- W4315488852 hasConcept C2775924081 @default.
- W4315488852 hasConcept C2777021972 @default.
- W4315488852 hasConcept C2777303404 @default.
- W4315488852 hasConcept C2780704645 @default.
- W4315488852 hasConcept C28826006 @default.
- W4315488852 hasConcept C32848918 @default.
- W4315488852 hasConcept C33923547 @default.
- W4315488852 hasConcept C36299963 @default.
- W4315488852 hasConcept C37404715 @default.
- W4315488852 hasConcept C41008148 @default.
- W4315488852 hasConcept C47446073 @default.
- W4315488852 hasConcept C50522688 @default.
- W4315488852 hasConcept C55493867 @default.
- W4315488852 hasConcept C62520636 @default.
- W4315488852 hasConcept C6557445 @default.
- W4315488852 hasConcept C86803240 @default.
- W4315488852 hasConcept C91575142 @default.
- W4315488852 hasConcept C98779006 @default.
- W4315488852 hasConceptScore W4315488852C104317684 @default.
- W4315488852 hasConceptScore W4315488852C121332964 @default.
- W4315488852 hasConceptScore W4315488852C126255220 @default.
- W4315488852 hasConceptScore W4315488852C134306372 @default.
- W4315488852 hasConceptScore W4315488852C137836250 @default.
- W4315488852 hasConceptScore W4315488852C154945302 @default.
- W4315488852 hasConceptScore W4315488852C162324750 @default.
- W4315488852 hasConceptScore W4315488852C185592680 @default.
- W4315488852 hasConceptScore W4315488852C203479927 @default.
- W4315488852 hasConceptScore W4315488852C204241405 @default.
- W4315488852 hasConceptScore W4315488852C204495892 @default.
- W4315488852 hasConceptScore W4315488852C2775924081 @default.
- W4315488852 hasConceptScore W4315488852C2777021972 @default.
- W4315488852 hasConceptScore W4315488852C2777303404 @default.
- W4315488852 hasConceptScore W4315488852C2780704645 @default.
- W4315488852 hasConceptScore W4315488852C28826006 @default.
- W4315488852 hasConceptScore W4315488852C32848918 @default.
- W4315488852 hasConceptScore W4315488852C33923547 @default.
- W4315488852 hasConceptScore W4315488852C36299963 @default.
- W4315488852 hasConceptScore W4315488852C37404715 @default.
- W4315488852 hasConceptScore W4315488852C41008148 @default.
- W4315488852 hasConceptScore W4315488852C47446073 @default.
- W4315488852 hasConceptScore W4315488852C50522688 @default.
- W4315488852 hasConceptScore W4315488852C55493867 @default.
- W4315488852 hasConceptScore W4315488852C62520636 @default.
- W4315488852 hasConceptScore W4315488852C6557445 @default.
- W4315488852 hasConceptScore W4315488852C86803240 @default.
- W4315488852 hasConceptScore W4315488852C91575142 @default.
- W4315488852 hasConceptScore W4315488852C98779006 @default.
- W4315488852 hasFunder F4320321408 @default.
- W4315488852 hasFunder F4320326925 @default.