Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900809720> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2900809720 endingPage "227" @default.
- W2900809720 startingPage "221" @default.
- W2900809720 abstract "In this paper, we identify a class of input constrained optimal control problems which can be approximately solved using Reinforcement Learning (RL) approaches. We start with a general class of problems which do not admit the theoretical assumptions used to derive RL frameworks. We then restrict this class by extra conditions on the dynamics and the objective function as deemed necessary. Our attention concerns two assumptions: (i) the smoothness of the value function which is typically not satisfied in input constrained problems, and (ii) the form of the objective function which can be more general than what has been proposed in previous formulations. For the first assumption, we use the method of vanishing viscosity to derive the conditions under which RL approaches can be used to find an approximate solution. These conditions relax a differentiability assumption to a continuity assumption of the value function thereby extending the applicability of RL frameworks. For the second assumption, we generalize the specific integrand form of the control cost used in previous formations to a more general class of cost functions that guarantee continuity of the control policy. Using these results, we present a new partially model-free RL framework for optimal control of input constrained continuous-time systems. Our RL framework requires an initial stabilizing policy and guarantees uniformly ultimate boundedness of the state variables. We demonstrate our results by simulation examples." @default.
- W2900809720 created "2018-11-29" @default.
- W2900809720 creator A5036304677 @default.
- W2900809720 creator A5089213370 @default.
- W2900809720 date "2019-01-01" @default.
- W2900809720 modified "2023-10-16" @default.
- W2900809720 title "Reinforcement learning for a class of continuous-time input constrained optimal control problems" @default.
- W2900809720 cites W1564711114 @default.
- W2900809720 cites W1863485266 @default.
- W2900809720 cites W1979406133 @default.
- W2900809720 cites W2011833550 @default.
- W2900809720 cites W2012451615 @default.
- W2900809720 cites W2013895638 @default.
- W2900809720 cites W2027438381 @default.
- W2900809720 cites W2031727844 @default.
- W2900809720 cites W2059722814 @default.
- W2900809720 cites W2081514674 @default.
- W2900809720 cites W2085194340 @default.
- W2900809720 cites W2091565802 @default.
- W2900809720 cites W2148439597 @default.
- W2900809720 cites W2160561608 @default.
- W2900809720 cites W2165726932 @default.
- W2900809720 cites W2749408143 @default.
- W2900809720 cites W3103456419 @default.
- W2900809720 doi "https://doi.org/10.1016/j.automatica.2018.10.038" @default.
- W2900809720 hasPublicationYear "2019" @default.
- W2900809720 type Work @default.
- W2900809720 sameAs 2900809720 @default.
- W2900809720 citedByCount "27" @default.
- W2900809720 countsByYear W29008097202019 @default.
- W2900809720 countsByYear W29008097202020 @default.
- W2900809720 countsByYear W29008097202021 @default.
- W2900809720 countsByYear W29008097202022 @default.
- W2900809720 countsByYear W29008097202023 @default.
- W2900809720 crossrefType "journal-article" @default.
- W2900809720 hasAuthorship W2900809720A5036304677 @default.
- W2900809720 hasAuthorship W2900809720A5089213370 @default.
- W2900809720 hasConcept C102634674 @default.
- W2900809720 hasConcept C11413529 @default.
- W2900809720 hasConcept C126255220 @default.
- W2900809720 hasConcept C134306372 @default.
- W2900809720 hasConcept C14036430 @default.
- W2900809720 hasConcept C14646407 @default.
- W2900809720 hasConcept C154945302 @default.
- W2900809720 hasConcept C202615002 @default.
- W2900809720 hasConcept C2777212361 @default.
- W2900809720 hasConcept C33923547 @default.
- W2900809720 hasConcept C41008148 @default.
- W2900809720 hasConcept C48103436 @default.
- W2900809720 hasConcept C78458016 @default.
- W2900809720 hasConcept C86803240 @default.
- W2900809720 hasConcept C91575142 @default.
- W2900809720 hasConcept C97541855 @default.
- W2900809720 hasConceptScore W2900809720C102634674 @default.
- W2900809720 hasConceptScore W2900809720C11413529 @default.
- W2900809720 hasConceptScore W2900809720C126255220 @default.
- W2900809720 hasConceptScore W2900809720C134306372 @default.
- W2900809720 hasConceptScore W2900809720C14036430 @default.
- W2900809720 hasConceptScore W2900809720C14646407 @default.
- W2900809720 hasConceptScore W2900809720C154945302 @default.
- W2900809720 hasConceptScore W2900809720C202615002 @default.
- W2900809720 hasConceptScore W2900809720C2777212361 @default.
- W2900809720 hasConceptScore W2900809720C33923547 @default.
- W2900809720 hasConceptScore W2900809720C41008148 @default.
- W2900809720 hasConceptScore W2900809720C48103436 @default.
- W2900809720 hasConceptScore W2900809720C78458016 @default.
- W2900809720 hasConceptScore W2900809720C86803240 @default.
- W2900809720 hasConceptScore W2900809720C91575142 @default.
- W2900809720 hasConceptScore W2900809720C97541855 @default.
- W2900809720 hasLocation W29008097201 @default.
- W2900809720 hasOpenAccess W2900809720 @default.
- W2900809720 hasPrimaryLocation W29008097201 @default.
- W2900809720 hasRelatedWork W1985081576 @default.
- W2900809720 hasRelatedWork W2033346654 @default.
- W2900809720 hasRelatedWork W2072026208 @default.
- W2900809720 hasRelatedWork W2175104911 @default.
- W2900809720 hasRelatedWork W2342906992 @default.
- W2900809720 hasRelatedWork W2968301050 @default.
- W2900809720 hasRelatedWork W3005633425 @default.
- W2900809720 hasRelatedWork W3123748881 @default.
- W2900809720 hasRelatedWork W4239477580 @default.
- W2900809720 hasRelatedWork W2183748016 @default.
- W2900809720 hasVolume "99" @default.
- W2900809720 isParatext "false" @default.
- W2900809720 isRetracted "false" @default.
- W2900809720 magId "2900809720" @default.
- W2900809720 workType "article" @default.