Matches in SemOpenAlex for { <https://semopenalex.org/work/W2152730650> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2152730650 abstract "Aiming to clarify the convergence or divergence conditions for Learning Classifier System (LCS), this paper explores: (1) an extreme condition where the reinforcement process of LCS diverges; and (2) methods to avoid such divergence. Based on our previous work that showed equivalence between LCS's reinforcement process and Reinforcement Learning (RL) with Function approximation (FA) method, we present a counter-example for LCS with Q-bucket-brigade based on the 11-state star problem, a counter-example originally proposed to show the divergence of Q-learning with linear FA. Furthermore, the empirical results applying the counter-example to LCS verified the results predicted from the theory: (1) LCS with Q-bucket-brigade diverged under the prediction problem, where the action selection policy was fixed; and (2) such divergence was avoided by using implicit-bucket-brigade or applying residual gradient algorithm to Q-bucket-brigade." @default.
- W2152730650 created "2016-06-24" @default.
- W2152730650 creator A5006972856 @default.
- W2152730650 creator A5064573074 @default.
- W2152730650 creator A5084452161 @default.
- W2152730650 date "2005-01-01" @default.
- W2152730650 modified "2023-09-27" @default.
- W2152730650 title "Counter example for Q-bucket-brigade under prediction problem" @default.
- W2152730650 cites W1505852642 @default.
- W2152730650 cites W1506349967 @default.
- W2152730650 cites W1515851193 @default.
- W2152730650 cites W1516897956 @default.
- W2152730650 cites W1517718593 @default.
- W2152730650 cites W1547105496 @default.
- W2152730650 cites W1646707810 @default.
- W2152730650 cites W1964928737 @default.
- W2152730650 cites W1965227651 @default.
- W2152730650 cites W1989101984 @default.
- W2152730650 cites W1999128321 @default.
- W2152730650 cites W2073677619 @default.
- W2152730650 cites W2100677568 @default.
- W2152730650 cites W2107277317 @default.
- W2152730650 cites W2112483970 @default.
- W2152730650 cites W2124175081 @default.
- W2152730650 cites W2125510930 @default.
- W2152730650 cites W2134367663 @default.
- W2152730650 cites W2139418546 @default.
- W2152730650 cites W2147750403 @default.
- W2152730650 cites W2150339816 @default.
- W2152730650 cites W2150459019 @default.
- W2152730650 cites W2152615835 @default.
- W2152730650 cites W2165131254 @default.
- W2152730650 cites W2169982856 @default.
- W2152730650 cites W2261323909 @default.
- W2152730650 cites W2480201967 @default.
- W2152730650 cites W3011120880 @default.
- W2152730650 cites W3028232160 @default.
- W2152730650 cites W2088618689 @default.
- W2152730650 doi "https://doi.org/10.1145/1102256.1102278" @default.
- W2152730650 hasPublicationYear "2005" @default.
- W2152730650 type Work @default.
- W2152730650 sameAs 2152730650 @default.
- W2152730650 citedByCount "5" @default.
- W2152730650 countsByYear W21527306502012 @default.
- W2152730650 countsByYear W21527306502017 @default.
- W2152730650 crossrefType "proceedings-article" @default.
- W2152730650 hasAuthorship W2152730650A5006972856 @default.
- W2152730650 hasAuthorship W2152730650A5064573074 @default.
- W2152730650 hasAuthorship W2152730650A5084452161 @default.
- W2152730650 hasConcept C11413529 @default.
- W2152730650 hasConcept C118615104 @default.
- W2152730650 hasConcept C126255220 @default.
- W2152730650 hasConcept C138885662 @default.
- W2152730650 hasConcept C154945302 @default.
- W2152730650 hasConcept C162324750 @default.
- W2152730650 hasConcept C207390915 @default.
- W2152730650 hasConcept C2775924081 @default.
- W2152730650 hasConcept C2777303404 @default.
- W2152730650 hasConcept C2780069185 @default.
- W2152730650 hasConcept C33923547 @default.
- W2152730650 hasConcept C41008148 @default.
- W2152730650 hasConcept C41895202 @default.
- W2152730650 hasConcept C47446073 @default.
- W2152730650 hasConcept C50522688 @default.
- W2152730650 hasConcept C97541855 @default.
- W2152730650 hasConceptScore W2152730650C11413529 @default.
- W2152730650 hasConceptScore W2152730650C118615104 @default.
- W2152730650 hasConceptScore W2152730650C126255220 @default.
- W2152730650 hasConceptScore W2152730650C138885662 @default.
- W2152730650 hasConceptScore W2152730650C154945302 @default.
- W2152730650 hasConceptScore W2152730650C162324750 @default.
- W2152730650 hasConceptScore W2152730650C207390915 @default.
- W2152730650 hasConceptScore W2152730650C2775924081 @default.
- W2152730650 hasConceptScore W2152730650C2777303404 @default.
- W2152730650 hasConceptScore W2152730650C2780069185 @default.
- W2152730650 hasConceptScore W2152730650C33923547 @default.
- W2152730650 hasConceptScore W2152730650C41008148 @default.
- W2152730650 hasConceptScore W2152730650C41895202 @default.
- W2152730650 hasConceptScore W2152730650C47446073 @default.
- W2152730650 hasConceptScore W2152730650C50522688 @default.
- W2152730650 hasConceptScore W2152730650C97541855 @default.
- W2152730650 hasLocation W21527306501 @default.
- W2152730650 hasOpenAccess W2152730650 @default.
- W2152730650 hasPrimaryLocation W21527306501 @default.
- W2152730650 hasRelatedWork W1517908938 @default.
- W2152730650 hasRelatedWork W1562959674 @default.
- W2152730650 hasRelatedWork W1680548566 @default.
- W2152730650 hasRelatedWork W2071310731 @default.
- W2152730650 hasRelatedWork W2122222693 @default.
- W2152730650 hasRelatedWork W2923653485 @default.
- W2152730650 hasRelatedWork W2957776456 @default.
- W2152730650 hasRelatedWork W4361026739 @default.
- W2152730650 hasRelatedWork W4361253176 @default.
- W2152730650 hasRelatedWork W2745007822 @default.
- W2152730650 isParatext "false" @default.
- W2152730650 isRetracted "false" @default.
- W2152730650 magId "2152730650" @default.
- W2152730650 workType "article" @default.