Matches in SemOpenAlex for { <https://semopenalex.org/work/W54337410> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W54337410 endingPage "793" @default.
- W54337410 startingPage "784" @default.
- W54337410 abstract "The success of Learning Automata (LA)-based estimator algorithms over the classical, Linear Reward-Inaction (L RI )-like schemes, can be explained by their ability to pursue the actions with the highest reward probability estimates. Without access to reward probability estimates, it makes sense for schemes like the L RI to first make large exploring steps, and then to gradually turn exploration into exploitation by making progressively smaller learning steps. However, this behavior becomes counter-intuitive when pursuing actions based on their estimated reward probabilities. Learning should then ideally proceed in progressively larger steps, as the reward probability estimates turn more accurate. This paper introduces a new estimator algorithm, the Discretized Bayesian Pursuit Algorithm (DBPA), that achieves this. The DBPA is implemented by linearly discretizing the action probability space of the Bayesian Pursuit Algorithm (BPA) [1]. The key innovation is that the linear discrete updating rules mitigate the counter-intuitive behavior of the corresponding linear continuous updating rules, by augmenting them with the reward probability estimates. Extensive experimental results show the superiority of DBPA over previous estimator algorithms. Indeed, the DBPA is probably the fastest reported LA to date." @default.
- W54337410 created "2016-06-24" @default.
- W54337410 creator A5016622484 @default.
- W54337410 creator A5055634885 @default.
- W54337410 creator A5071922620 @default.
- W54337410 date "2012-01-01" @default.
- W54337410 modified "2023-10-16" @default.
- W54337410 title "Discretized Bayesian Pursuit – A New Scheme for Reinforcement Learning" @default.
- W54337410 cites W1996494912 @default.
- W54337410 cites W2030501831 @default.
- W54337410 cites W2039522160 @default.
- W54337410 cites W2066302983 @default.
- W54337410 cites W2097272820 @default.
- W54337410 cites W2146350180 @default.
- W54337410 cites W2152005431 @default.
- W54337410 cites W2158832545 @default.
- W54337410 cites W2162961538 @default.
- W54337410 cites W2162964807 @default.
- W54337410 cites W2164823136 @default.
- W54337410 cites W4234150660 @default.
- W54337410 doi "https://doi.org/10.1007/978-3-642-31087-4_79" @default.
- W54337410 hasPublicationYear "2012" @default.
- W54337410 type Work @default.
- W54337410 sameAs 54337410 @default.
- W54337410 citedByCount "16" @default.
- W54337410 countsByYear W543374102013 @default.
- W54337410 countsByYear W543374102015 @default.
- W54337410 countsByYear W543374102016 @default.
- W54337410 countsByYear W543374102018 @default.
- W54337410 countsByYear W543374102019 @default.
- W54337410 countsByYear W543374102020 @default.
- W54337410 countsByYear W543374102022 @default.
- W54337410 countsByYear W543374102023 @default.
- W54337410 crossrefType "book-chapter" @default.
- W54337410 hasAuthorship W54337410A5016622484 @default.
- W54337410 hasAuthorship W54337410A5055634885 @default.
- W54337410 hasAuthorship W54337410A5071922620 @default.
- W54337410 hasConcept C105795698 @default.
- W54337410 hasConcept C107673813 @default.
- W54337410 hasConcept C112505250 @default.
- W54337410 hasConcept C11413529 @default.
- W54337410 hasConcept C119857082 @default.
- W54337410 hasConcept C126255220 @default.
- W54337410 hasConcept C134306372 @default.
- W54337410 hasConcept C154945302 @default.
- W54337410 hasConcept C160234255 @default.
- W54337410 hasConcept C185429906 @default.
- W54337410 hasConcept C2776807809 @default.
- W54337410 hasConcept C33923547 @default.
- W54337410 hasConcept C41008148 @default.
- W54337410 hasConcept C73000952 @default.
- W54337410 hasConcept C97541855 @default.
- W54337410 hasConceptScore W54337410C105795698 @default.
- W54337410 hasConceptScore W54337410C107673813 @default.
- W54337410 hasConceptScore W54337410C112505250 @default.
- W54337410 hasConceptScore W54337410C11413529 @default.
- W54337410 hasConceptScore W54337410C119857082 @default.
- W54337410 hasConceptScore W54337410C126255220 @default.
- W54337410 hasConceptScore W54337410C134306372 @default.
- W54337410 hasConceptScore W54337410C154945302 @default.
- W54337410 hasConceptScore W54337410C160234255 @default.
- W54337410 hasConceptScore W54337410C185429906 @default.
- W54337410 hasConceptScore W54337410C2776807809 @default.
- W54337410 hasConceptScore W54337410C33923547 @default.
- W54337410 hasConceptScore W54337410C41008148 @default.
- W54337410 hasConceptScore W54337410C73000952 @default.
- W54337410 hasConceptScore W54337410C97541855 @default.
- W54337410 hasLocation W543374101 @default.
- W54337410 hasOpenAccess W54337410 @default.
- W54337410 hasPrimaryLocation W543374101 @default.
- W54337410 hasRelatedWork W2110658950 @default.
- W54337410 hasRelatedWork W2765250768 @default.
- W54337410 hasRelatedWork W2959276766 @default.
- W54337410 hasRelatedWork W2961085424 @default.
- W54337410 hasRelatedWork W2963627453 @default.
- W54337410 hasRelatedWork W3033035387 @default.
- W54337410 hasRelatedWork W3074294383 @default.
- W54337410 hasRelatedWork W3080853598 @default.
- W54337410 hasRelatedWork W4206669594 @default.
- W54337410 hasRelatedWork W4319083788 @default.
- W54337410 isParatext "false" @default.
- W54337410 isRetracted "false" @default.
- W54337410 magId "54337410" @default.
- W54337410 workType "book-chapter" @default.