{"@context":["https://w3id.org/fdo/context/v1",{"schema":"https://schema.org/","prov":"http://www.w3.org/ns/prov#","fdo":"https://w3id.org/fdo/vocabulary/"}],"@id":"https://fdo.portal.mardi4nfdi.de/fdo/Q1898166","@type":"DigitalObject","kernel":{"@id":"https://fdo.portal.mardi4nfdi.de/fdo/Q1898166","digitalObjectType":"https://schema.org/ScholarlyArticle","primaryIdentifier":"mardi:Q1898166","kernelVersion":"v1","immutable":true,"modified":"2026-01-01T12:09:44Z"},"profile":{"@context":"https://schema.org","@type":"ScholarlyArticle","@id":"https://portal.mardi4nfdi.de/entity/Q1898166","name":"Continuous action set learning automata for stochastic optimization","headline":"Continuous action set learning automata for stochastic optimization","description":"scientific article; zbMATH DE number 799598","url":"https://portal.mardi4nfdi.de/entity/Q1898166","datePublished":"1996-05-30","author":[{"@id":"https://portal.mardi4nfdi.de/entity/Q1898165"},{"@id":"https://portal.mardi4nfdi.de/entity/Q229977"},{"@id":"https://portal.mardi4nfdi.de/entity/Q229980"}],"publisher":[{"@id":"https://portal.mardi4nfdi.de/entity/Q164292"}],"identifier":{"@type":"PropertyValue","propertyID":"doi","value":"10.1016/0016-0032(94)90039-6","url":"https://doi.org/10.1016/0016-0032(94)90039-6"},"sameAs":["https://doi.org/10.1016/0016-0032(94)90039-6"],"comment":"The paper deals with the minimization of a function whose values cannot be determined exactly. However, it is assumed that it is possible (at any chosen point) to observe a random element with the mathematical expectation equal to the corresponding function value. Such situation appears for example in pattern recognition, signal processing, etc. It is well-known, from the mathematical optimization theory, that the stochastic approximation method can be employed to solve the above-mentioned problem. The other possibility is to employ a random search procedure.   This investigation deals with an adaptive search procedure that generalizes the traditional model of a learning automaton. The Gaussian distribution is employed. This type of distribution is determined only by two parameters in the one-dimensional case, and by a finite number of parameters in general case. The one-dimensional case and multidimensional case are investigated separately.   The convergence properties of the algorithm are investigated theoretically. Simulation results are presented at the end.","citation":[{"@id":"https://portal.mardi4nfdi.de/entity/Q4403756"},{"@id":"https://portal.mardi4nfdi.de/entity/Q5816980"},{"@id":"https://portal.mardi4nfdi.de/entity/Q5829436"},{"@id":"https://portal.mardi4nfdi.de/entity/Q4006251"},{"@id":"https://portal.mardi4nfdi.de/entity/Q2525478"},{"@id":"https://portal.mardi4nfdi.de/entity/Q3968769"},{"@id":"https://portal.mardi4nfdi.de/entity/Q3771625"},{"@id":"https://portal.mardi4nfdi.de/entity/Q3344923"},{"@id":"https://portal.mardi4nfdi.de/entity/Q1812928"},{"@id":"https://portal.mardi4nfdi.de/entity/Q1898166"},{"@id":"https://portal.mardi4nfdi.de/entity/Q1813720"},{"@id":"https://portal.mardi4nfdi.de/entity/Q5560061"}]},"provenance":{"prov:generatedAtTime":"2026-01-01T12:09:44Z","prov:wasAttributedTo":"MaRDI Knowledge Graph"}}