Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947983460> ?p ?o ?g. }
- W2947983460 abstract "We propose controller synthesis for state regulation problems in which a human operator shares control with an autonomy system, running in parallel. The autonomy system continuously improves over human action, with minimal intervention, and can take over full-control. It additively combines user input with an adaptive optimal corrective signal. It is adaptive in that it neither estimates nor requires a model of the human's action policy, or the internal dynamics of the plant, and can adjust to changes in both. Our contribution is twofold; first, a new synthesis for shared control which we formulate as an adaptive optimal control problem for continuous-time linear systems and solve it online as a human-in-the-loop reinforcement learning. The result is an architecture that we call shared linear quadratic regulator (sLQR). Second, we provide new analysis of reinforcement learning for continuous-time linear systems in two parts. In the first analysis part, we avoid learning along a single state-space trajectory which we show leads to data collinearity under certain conditions. We make a clear separation between exploitation of learned policies and exploration of the state-space, and propose an exploration scheme that requires switching to new state-space trajectories rather than injecting noise continuously while learning. This avoidance of continuous noise injection minimizes interference with human action, and avoids bias in the convergence to the stabilizing solution of the underlying algebraic Riccati equation. We show that exploring a minimum number of pairwise distinct state-space trajectories is necessary to avoid collinearity in the learning data. In the second analysis part, we show conditions under which existence and uniqueness of solutions can be established for off-policy reinforcement learning in continuous-time linear systems; namely, prior knowledge of the input matrix." @default.
- W2947983460 created "2019-06-07" @default.
- W2947983460 creator A5009970921 @default.
- W2947983460 creator A5066830185 @default.
- W2947983460 creator A5081073767 @default.
- W2947983460 date "2019-05-27" @default.
- W2947983460 modified "2023-09-27" @default.
- W2947983460 title "Shared Linear Quadratic Regulation Control: A Reinforcement Learning Approach" @default.
- W2947983460 cites W1969732712 @default.
- W2947983460 cites W1985574396 @default.
- W2947983460 cites W2024303516 @default.
- W2947983460 cites W2037025184 @default.
- W2947983460 cites W2051987861 @default.
- W2947983460 cites W2095590702 @default.
- W2947983460 cites W2105925198 @default.
- W2947983460 cites W2108286682 @default.
- W2947983460 cites W2148439597 @default.
- W2947983460 cites W2160561608 @default.
- W2947983460 cites W2333120204 @default.
- W2947983460 cites W2508598219 @default.
- W2947983460 cites W2593797937 @default.
- W2947983460 cites W2773226774 @default.
- W2947983460 cites W2786110872 @default.
- W2947983460 cites W2790958326 @default.
- W2947983460 cites W2962776080 @default.
- W2947983460 cites W2963366811 @default.
- W2947983460 cites W3149738779 @default.
- W2947983460 hasPublicationYear "2019" @default.
- W2947983460 type Work @default.
- W2947983460 sameAs 2947983460 @default.
- W2947983460 citedByCount "0" @default.
- W2947983460 crossrefType "posted-content" @default.
- W2947983460 hasAuthorship W2947983460A5009970921 @default.
- W2947983460 hasAuthorship W2947983460A5066830185 @default.
- W2947983460 hasAuthorship W2947983460A5081073767 @default.
- W2947983460 hasConcept C105795698 @default.
- W2947983460 hasConcept C107464732 @default.
- W2947983460 hasConcept C121332964 @default.
- W2947983460 hasConcept C126255220 @default.
- W2947983460 hasConcept C1276947 @default.
- W2947983460 hasConcept C134306372 @default.
- W2947983460 hasConcept C13662910 @default.
- W2947983460 hasConcept C13847129 @default.
- W2947983460 hasConcept C154945302 @default.
- W2947983460 hasConcept C203479927 @default.
- W2947983460 hasConcept C2775924081 @default.
- W2947983460 hasConcept C33923547 @default.
- W2947983460 hasConcept C41008148 @default.
- W2947983460 hasConcept C45473103 @default.
- W2947983460 hasConcept C47446073 @default.
- W2947983460 hasConcept C6557445 @default.
- W2947983460 hasConcept C6802819 @default.
- W2947983460 hasConcept C72434380 @default.
- W2947983460 hasConcept C78045399 @default.
- W2947983460 hasConcept C86803240 @default.
- W2947983460 hasConcept C97541855 @default.
- W2947983460 hasConcept C98779006 @default.
- W2947983460 hasConceptScore W2947983460C105795698 @default.
- W2947983460 hasConceptScore W2947983460C107464732 @default.
- W2947983460 hasConceptScore W2947983460C121332964 @default.
- W2947983460 hasConceptScore W2947983460C126255220 @default.
- W2947983460 hasConceptScore W2947983460C1276947 @default.
- W2947983460 hasConceptScore W2947983460C134306372 @default.
- W2947983460 hasConceptScore W2947983460C13662910 @default.
- W2947983460 hasConceptScore W2947983460C13847129 @default.
- W2947983460 hasConceptScore W2947983460C154945302 @default.
- W2947983460 hasConceptScore W2947983460C203479927 @default.
- W2947983460 hasConceptScore W2947983460C2775924081 @default.
- W2947983460 hasConceptScore W2947983460C33923547 @default.
- W2947983460 hasConceptScore W2947983460C41008148 @default.
- W2947983460 hasConceptScore W2947983460C45473103 @default.
- W2947983460 hasConceptScore W2947983460C47446073 @default.
- W2947983460 hasConceptScore W2947983460C6557445 @default.
- W2947983460 hasConceptScore W2947983460C6802819 @default.
- W2947983460 hasConceptScore W2947983460C72434380 @default.
- W2947983460 hasConceptScore W2947983460C78045399 @default.
- W2947983460 hasConceptScore W2947983460C86803240 @default.
- W2947983460 hasConceptScore W2947983460C97541855 @default.
- W2947983460 hasConceptScore W2947983460C98779006 @default.
- W2947983460 hasLocation W29479834601 @default.
- W2947983460 hasOpenAccess W2947983460 @default.
- W2947983460 hasPrimaryLocation W29479834601 @default.
- W2947983460 hasRelatedWork W1538918057 @default.
- W2947983460 hasRelatedWork W1621708194 @default.
- W2947983460 hasRelatedWork W1967780961 @default.
- W2947983460 hasRelatedWork W2097451572 @default.
- W2947983460 hasRelatedWork W2154549708 @default.
- W2947983460 hasRelatedWork W2397557326 @default.
- W2947983460 hasRelatedWork W2482698326 @default.
- W2947983460 hasRelatedWork W2616431752 @default.
- W2947983460 hasRelatedWork W2780720505 @default.
- W2947983460 hasRelatedWork W2910124058 @default.
- W2947983460 hasRelatedWork W2919701918 @default.
- W2947983460 hasRelatedWork W2965749647 @default.
- W2947983460 hasRelatedWork W2991030916 @default.
- W2947983460 hasRelatedWork W2998672046 @default.
- W2947983460 hasRelatedWork W3011773518 @default.
- W2947983460 hasRelatedWork W3014975158 @default.
- W2947983460 hasRelatedWork W3022519106 @default.
- W2947983460 hasRelatedWork W3042051570 @default.