Matches in SemOpenAlex for { <https://semopenalex.org/work/W2154549708> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2154549708 endingPage "217" @default.
- W2154549708 startingPage "163" @default.
- W2154549708 abstract "A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state. The function is important because an agent can use this measure to decide what to do next. A common problem in reinforcement learning when applied to systems having continuous states and action spaces is that the value function must operate with a domain consisting of real-valued variables, which means that it should be able to represent the value of infinitely many state and action pairs. For this reason, function approximators are used to represent the value function when a close-form solution of the optimal policy is not available. In this article, we extend a previously proposed reinforcement learning algorithm so that it can be used with function approximators that generalize the value of individual experiences across both state and action spaces. In particular, we discuss the benefits of using sparse coarse-coded function approximators to represent value functions and describe in detail three implementations: cerebellar model articulation controllers, instance-based, and case-based. Additionally, we discuss how function approximators having different degrees of resolution in different regions of the state and action spaces may influence the performance and learning efficiency of the agent. We propose a simple and modular technique that can be used to implement function approximators with nonuniform degrees of resolution so that the value function can be represented with higher accuracy in important regions of the state and action spaces. We performed extensive experiments in the double-integrator and pendulum swing-up systems to demonstrate the proposed ideas. '" @default.
- W2154549708 created "2016-06-24" @default.
- W2154549708 creator A5004923102 @default.
- W2154549708 creator A5028084240 @default.
- W2154549708 creator A5044452407 @default.
- W2154549708 date "1997-09-01" @default.
- W2154549708 modified "2023-10-01" @default.
- W2154549708 title "Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces" @default.
- W2154549708 cites W1969420452 @default.
- W2154549708 cites W1986241547 @default.
- W2154549708 cites W1993740947 @default.
- W2154549708 cites W2104122126 @default.
- W2154549708 cites W2113913482 @default.
- W2154549708 cites W2139418546 @default.
- W2154549708 cites W3041202696 @default.
- W2154549708 cites W4231226883 @default.
- W2154549708 doi "https://doi.org/10.1177/105971239700600201" @default.
- W2154549708 hasPublicationYear "1997" @default.
- W2154549708 type Work @default.
- W2154549708 sameAs 2154549708 @default.
- W2154549708 citedByCount "231" @default.
- W2154549708 countsByYear W21545497082012 @default.
- W2154549708 countsByYear W21545497082013 @default.
- W2154549708 countsByYear W21545497082014 @default.
- W2154549708 countsByYear W21545497082015 @default.
- W2154549708 countsByYear W21545497082016 @default.
- W2154549708 countsByYear W21545497082017 @default.
- W2154549708 countsByYear W21545497082018 @default.
- W2154549708 countsByYear W21545497082019 @default.
- W2154549708 countsByYear W21545497082020 @default.
- W2154549708 countsByYear W21545497082021 @default.
- W2154549708 countsByYear W21545497082022 @default.
- W2154549708 countsByYear W21545497082023 @default.
- W2154549708 crossrefType "journal-article" @default.
- W2154549708 hasAuthorship W2154549708A5004923102 @default.
- W2154549708 hasAuthorship W2154549708A5028084240 @default.
- W2154549708 hasAuthorship W2154549708A5044452407 @default.
- W2154549708 hasBestOaLocation W21545497082 @default.
- W2154549708 hasConcept C121332964 @default.
- W2154549708 hasConcept C124101348 @default.
- W2154549708 hasConcept C126255220 @default.
- W2154549708 hasConcept C14036430 @default.
- W2154549708 hasConcept C14646407 @default.
- W2154549708 hasConcept C154945302 @default.
- W2154549708 hasConcept C188116033 @default.
- W2154549708 hasConcept C2780009758 @default.
- W2154549708 hasConcept C2780791683 @default.
- W2154549708 hasConcept C33923547 @default.
- W2154549708 hasConcept C41008148 @default.
- W2154549708 hasConcept C62520636 @default.
- W2154549708 hasConcept C78458016 @default.
- W2154549708 hasConcept C86803240 @default.
- W2154549708 hasConcept C97541855 @default.
- W2154549708 hasConceptScore W2154549708C121332964 @default.
- W2154549708 hasConceptScore W2154549708C124101348 @default.
- W2154549708 hasConceptScore W2154549708C126255220 @default.
- W2154549708 hasConceptScore W2154549708C14036430 @default.
- W2154549708 hasConceptScore W2154549708C14646407 @default.
- W2154549708 hasConceptScore W2154549708C154945302 @default.
- W2154549708 hasConceptScore W2154549708C188116033 @default.
- W2154549708 hasConceptScore W2154549708C2780009758 @default.
- W2154549708 hasConceptScore W2154549708C2780791683 @default.
- W2154549708 hasConceptScore W2154549708C33923547 @default.
- W2154549708 hasConceptScore W2154549708C41008148 @default.
- W2154549708 hasConceptScore W2154549708C62520636 @default.
- W2154549708 hasConceptScore W2154549708C78458016 @default.
- W2154549708 hasConceptScore W2154549708C86803240 @default.
- W2154549708 hasConceptScore W2154549708C97541855 @default.
- W2154549708 hasIssue "2" @default.
- W2154549708 hasLocation W21545497081 @default.
- W2154549708 hasLocation W21545497082 @default.
- W2154549708 hasOpenAccess W2154549708 @default.
- W2154549708 hasPrimaryLocation W21545497081 @default.
- W2154549708 hasRelatedWork W2025663273 @default.
- W2154549708 hasRelatedWork W2089415692 @default.
- W2154549708 hasRelatedWork W2373808749 @default.
- W2154549708 hasRelatedWork W2937181779 @default.
- W2154549708 hasRelatedWork W2984109677 @default.
- W2154549708 hasRelatedWork W3038962357 @default.
- W2154549708 hasRelatedWork W3115089987 @default.
- W2154549708 hasRelatedWork W4378771262 @default.
- W2154549708 hasRelatedWork W4382050307 @default.
- W2154549708 hasRelatedWork W4387019592 @default.
- W2154549708 hasVolume "6" @default.
- W2154549708 isParatext "false" @default.
- W2154549708 isRetracted "false" @default.
- W2154549708 magId "2154549708" @default.
- W2154549708 workType "article" @default.