Reinforcement learning for symbolic expression induction

Vogiatzis, D; Stafylopatis, A

dc.contributor.author	Vogiatzis, D	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T01:15:51Z
dc.date.available	2014-03-01T01:15:51Z
dc.date.issued	2000	en
dc.identifier.issn	0378-4754	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13777
dc.subject	neural networks	en
dc.subject	reinforcement learning	en
dc.subject	symbolic/subsymbolic processing	en
dc.subject	rule extraction	en
dc.subject.classification	Computer Science, Interdisciplinary Applications	en
dc.subject.classification	Computer Science, Software Engineering	en
dc.subject.classification	Mathematics, Applied	en
dc.subject.other	Artificial neural networks	en
dc.title	Reinforcement learning for symbolic expression induction	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S0378-4754(99)00115-9	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S0378-4754(99)00115-9	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	We propose a neural network method for the generation of symbolic expressions using reinforcement learning. Usually, the symbolic form expressed in terms of a calculus (propositional, first-order, lambda, etc.) is deemed comprehensible by humans and it is necessary as far as the acceptance of neural networks is concerned. According to the proposed method, a human decides on the kind and number of primitive functions which, with the appropriate composition (in the mathematical sense), can represent a mapping between two domains. The appropriate composition is achieved by an agent which tries many compositions and receives a reward depending on the quality of the composed function. Naturally, the learning agent (which in our case is a recurrent neural net) must perform the credit assignment task. Results are encouraging concerning the derivation of simple arithmetic expressions. (C) 2000 IMACS/Elsevier Science B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	MATHEMATICS AND COMPUTERS IN SIMULATION	en
dc.identifier.doi	10.1016/S0378-4754(99)00115-9	en
dc.identifier.isi	ISI:000084223700004	en
dc.identifier.volume	51	en
dc.identifier.issue	3-4	en
dc.identifier.spage	169	en
dc.identifier.epage	179	en