Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092567899> ?p ?o ?g. }
- W3092567899 abstract "We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional continuous latent state with linear dynamics and quadratic costs, but the agent operates on high-dimensional, nonlinear observations such as images from a camera. To enable sample-efficient learning, we assume that the learner has access to a class of decoder functions (e.g., neural networks) that is flexible enough to capture the mapping from observations to latent states. We introduce a new algorithm, RichID, which learns a near-optimal policy for the RichLQR with sample complexity scaling only with the dimension of the latent state space and the capacity of the decoder function class. RichID is oracle-efficient and accesses the decoder class only through calls to a least-squares regression oracle. Our results constitute the first provable sample complexity guarantee for continuous control with an unknown nonlinearity in the system model and general function approximation." @default.
- W3092567899 created "2020-10-15" @default.
- W3092567899 creator A5005003250 @default.
- W3092567899 creator A5015082848 @default.
- W3092567899 creator A5032266950 @default.
- W3092567899 creator A5033128676 @default.
- W3092567899 creator A5037154191 @default.
- W3092567899 creator A5075069827 @default.
- W3092567899 creator A5076656836 @default.
- W3092567899 creator A5088218114 @default.
- W3092567899 date "2020-10-08" @default.
- W3092567899 modified "2023-09-23" @default.
- W3092567899 title "Learning the Linear Quadratic Regulator from Nonlinear Observations" @default.
- W3092567899 cites W107583932 @default.
- W3092567899 cites W1560153690 @default.
- W3092567899 cites W1786332878 @default.
- W3092567899 cites W1970377488 @default.
- W3092567899 cites W1975677447 @default.
- W3092567899 cites W2052044664 @default.
- W3092567899 cites W2057815328 @default.
- W3092567899 cites W2067994512 @default.
- W3092567899 cites W2098432798 @default.
- W3092567899 cites W2541714257 @default.
- W3092567899 cites W2545659366 @default.
- W3092567899 cites W2787248994 @default.
- W3092567899 cites W2900152462 @default.
- W3092567899 cites W2912399346 @default.
- W3092567899 cites W2914473478 @default.
- W3092567899 cites W2963043564 @default.
- W3092567899 cites W2963402509 @default.
- W3092567899 cites W2963412706 @default.
- W3092567899 cites W2963430173 @default.
- W3092567899 cites W2964161785 @default.
- W3092567899 cites W2965010280 @default.
- W3092567899 cites W2965497096 @default.
- W3092567899 cites W2966289053 @default.
- W3092567899 cites W2970142535 @default.
- W3092567899 cites W2972915637 @default.
- W3092567899 cites W2995322606 @default.
- W3092567899 cites W3007678396 @default.
- W3092567899 cites W3013318022 @default.
- W3092567899 cites W3035578948 @default.
- W3092567899 cites W3035642820 @default.
- W3092567899 cites W3035685037 @default.
- W3092567899 cites W3037364847 @default.
- W3092567899 cites W3046519016 @default.
- W3092567899 cites W3097602886 @default.
- W3092567899 cites W3102146195 @default.
- W3092567899 cites W3173645038 @default.
- W3092567899 cites W366592016 @default.
- W3092567899 cites W2963973933 @default.
- W3092567899 hasPublicationYear "2020" @default.
- W3092567899 type Work @default.
- W3092567899 sameAs 3092567899 @default.
- W3092567899 citedByCount "0" @default.
- W3092567899 crossrefType "posted-content" @default.
- W3092567899 hasAuthorship W3092567899A5005003250 @default.
- W3092567899 hasAuthorship W3092567899A5015082848 @default.
- W3092567899 hasAuthorship W3092567899A5032266950 @default.
- W3092567899 hasAuthorship W3092567899A5033128676 @default.
- W3092567899 hasAuthorship W3092567899A5037154191 @default.
- W3092567899 hasAuthorship W3092567899A5075069827 @default.
- W3092567899 hasAuthorship W3092567899A5076656836 @default.
- W3092567899 hasAuthorship W3092567899A5088218114 @default.
- W3092567899 hasConcept C11413529 @default.
- W3092567899 hasConcept C115903868 @default.
- W3092567899 hasConcept C121332964 @default.
- W3092567899 hasConcept C126255220 @default.
- W3092567899 hasConcept C129844170 @default.
- W3092567899 hasConcept C14036430 @default.
- W3092567899 hasConcept C154945302 @default.
- W3092567899 hasConcept C158622935 @default.
- W3092567899 hasConcept C202444582 @default.
- W3092567899 hasConcept C2524010 @default.
- W3092567899 hasConcept C2775924081 @default.
- W3092567899 hasConcept C2777212361 @default.
- W3092567899 hasConcept C33676613 @default.
- W3092567899 hasConcept C33923547 @default.
- W3092567899 hasConcept C41008148 @default.
- W3092567899 hasConcept C48103436 @default.
- W3092567899 hasConcept C50644808 @default.
- W3092567899 hasConcept C55166926 @default.
- W3092567899 hasConcept C62520636 @default.
- W3092567899 hasConcept C78458016 @default.
- W3092567899 hasConcept C86803240 @default.
- W3092567899 hasConcept C91575142 @default.
- W3092567899 hasConcept C91873725 @default.
- W3092567899 hasConcept C98779006 @default.
- W3092567899 hasConceptScore W3092567899C11413529 @default.
- W3092567899 hasConceptScore W3092567899C115903868 @default.
- W3092567899 hasConceptScore W3092567899C121332964 @default.
- W3092567899 hasConceptScore W3092567899C126255220 @default.
- W3092567899 hasConceptScore W3092567899C129844170 @default.
- W3092567899 hasConceptScore W3092567899C14036430 @default.
- W3092567899 hasConceptScore W3092567899C154945302 @default.
- W3092567899 hasConceptScore W3092567899C158622935 @default.
- W3092567899 hasConceptScore W3092567899C202444582 @default.
- W3092567899 hasConceptScore W3092567899C2524010 @default.
- W3092567899 hasConceptScore W3092567899C2775924081 @default.
- W3092567899 hasConceptScore W3092567899C2777212361 @default.