Matches in SemOpenAlex for { <https://semopenalex.org/work/W2160362462> ?p ?o ?g. }
- W2160362462 endingPage "549" @default.
- W2160362462 startingPage "535" @default.
- W2160362462 abstract "This paper provides a new Fuzzy Reinforcement Learning (FRL) algorithm based on critic-only architecture. The proposed algorithm, called Fuzzy Sarsa Learning (FSL), tunes the parameters of conclusion parts of the Fuzzy Inference System (FIS) online. Our FSL is based on Sarsa, which approximates the Action Value Function (AVF) and is an on-policy method. In each rule, actions are selected according to the proposed modified Softmax action selection so that the final inferred action selection probability in FSL is equivalent to the standard Softmax formula. We prove the existence of fixed points for the proposed Approximate Action Value Iteration (AAVI). Then, we show that FSL satisfies the necessary conditions that guarantee the existence of stationary points for it, which coincide with the fixed points of the AAVI. We prove that the weight vector of FSL with stationary action selection policy converges to a unique value. We also compare by simulation the performance of FSL and Fuzzy Q-Learning (FQL) in terms of learning speed, and action quality. Moreover, we show by another example the convergence of FSL and the divergence of FQL when both algorithms use a stationary policy. Copyright © 2008 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society" @default.
- W2160362462 created "2016-06-24" @default.
- W2160362462 creator A5017357124 @default.
- W2160362462 creator A5018349078 @default.
- W2160362462 creator A5072135442 @default.
- W2160362462 date "2008-10-01" @default.
- W2160362462 modified "2023-10-16" @default.
- W2160362462 title "Fuzzy Sarsa Learning and the proof of existence of its stationary points" @default.
- W2160362462 cites W1568229137 @default.
- W2160362462 cites W1583072328 @default.
- W2160362462 cites W1646707810 @default.
- W2160362462 cites W1820996291 @default.
- W2160362462 cites W1990687580 @default.
- W2160362462 cites W1994329139 @default.
- W2160362462 cites W2074606392 @default.
- W2160362462 cites W2083600812 @default.
- W2160362462 cites W2091565802 @default.
- W2160362462 cites W2106667095 @default.
- W2160362462 cites W2107726111 @default.
- W2160362462 cites W2111920136 @default.
- W2160362462 cites W2126357802 @default.
- W2160362462 cites W2139418546 @default.
- W2160362462 cites W2142196876 @default.
- W2160362462 cites W2150339816 @default.
- W2160362462 cites W2150999967 @default.
- W2160362462 cites W2305205647 @default.
- W2160362462 cites W32403112 @default.
- W2160362462 cites W4233696721 @default.
- W2160362462 cites W2034889985 @default.
- W2160362462 doi "https://doi.org/10.1002/asjc.54" @default.
- W2160362462 hasPublicationYear "2008" @default.
- W2160362462 type Work @default.
- W2160362462 sameAs 2160362462 @default.
- W2160362462 citedByCount "33" @default.
- W2160362462 countsByYear W21603624622012 @default.
- W2160362462 countsByYear W21603624622013 @default.
- W2160362462 countsByYear W21603624622014 @default.
- W2160362462 countsByYear W21603624622015 @default.
- W2160362462 countsByYear W21603624622016 @default.
- W2160362462 countsByYear W21603624622017 @default.
- W2160362462 countsByYear W21603624622018 @default.
- W2160362462 countsByYear W21603624622019 @default.
- W2160362462 countsByYear W21603624622020 @default.
- W2160362462 countsByYear W21603624622022 @default.
- W2160362462 countsByYear W21603624622023 @default.
- W2160362462 crossrefType "journal-article" @default.
- W2160362462 hasAuthorship W2160362462A5017357124 @default.
- W2160362462 hasAuthorship W2160362462A5018349078 @default.
- W2160362462 hasAuthorship W2160362462A5072135442 @default.
- W2160362462 hasConcept C121332964 @default.
- W2160362462 hasConcept C126255220 @default.
- W2160362462 hasConcept C134306372 @default.
- W2160362462 hasConcept C138885662 @default.
- W2160362462 hasConcept C154945302 @default.
- W2160362462 hasConcept C162324750 @default.
- W2160362462 hasConcept C166109690 @default.
- W2160362462 hasConcept C169760540 @default.
- W2160362462 hasConcept C188441871 @default.
- W2160362462 hasConcept C189237950 @default.
- W2160362462 hasConcept C207390915 @default.
- W2160362462 hasConcept C26760741 @default.
- W2160362462 hasConcept C2777303404 @default.
- W2160362462 hasConcept C2780791683 @default.
- W2160362462 hasConcept C28826006 @default.
- W2160362462 hasConcept C33923547 @default.
- W2160362462 hasConcept C41008148 @default.
- W2160362462 hasConcept C41895202 @default.
- W2160362462 hasConcept C50522688 @default.
- W2160362462 hasConcept C50644808 @default.
- W2160362462 hasConcept C58166 @default.
- W2160362462 hasConcept C61445026 @default.
- W2160362462 hasConcept C62520636 @default.
- W2160362462 hasConcept C86803240 @default.
- W2160362462 hasConcept C97541855 @default.
- W2160362462 hasConceptScore W2160362462C121332964 @default.
- W2160362462 hasConceptScore W2160362462C126255220 @default.
- W2160362462 hasConceptScore W2160362462C134306372 @default.
- W2160362462 hasConceptScore W2160362462C138885662 @default.
- W2160362462 hasConceptScore W2160362462C154945302 @default.
- W2160362462 hasConceptScore W2160362462C162324750 @default.
- W2160362462 hasConceptScore W2160362462C166109690 @default.
- W2160362462 hasConceptScore W2160362462C169760540 @default.
- W2160362462 hasConceptScore W2160362462C188441871 @default.
- W2160362462 hasConceptScore W2160362462C189237950 @default.
- W2160362462 hasConceptScore W2160362462C207390915 @default.
- W2160362462 hasConceptScore W2160362462C26760741 @default.
- W2160362462 hasConceptScore W2160362462C2777303404 @default.
- W2160362462 hasConceptScore W2160362462C2780791683 @default.
- W2160362462 hasConceptScore W2160362462C28826006 @default.
- W2160362462 hasConceptScore W2160362462C33923547 @default.
- W2160362462 hasConceptScore W2160362462C41008148 @default.
- W2160362462 hasConceptScore W2160362462C41895202 @default.
- W2160362462 hasConceptScore W2160362462C50522688 @default.
- W2160362462 hasConceptScore W2160362462C50644808 @default.
- W2160362462 hasConceptScore W2160362462C58166 @default.
- W2160362462 hasConceptScore W2160362462C61445026 @default.
- W2160362462 hasConceptScore W2160362462C62520636 @default.
- W2160362462 hasConceptScore W2160362462C86803240 @default.