ART-based neuro-fuzzy modelling applied to reinforcement learning

Zikidis, KC; Tzafestas, SG

dc.contributor.author	Zikidis, KC	en
dc.contributor.author	Tzafestas, SG	en
dc.date.accessioned	2014-03-01T02:42:12Z
dc.date.available	2014-03-01T02:42:12Z
dc.date.issued	2003	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30858
dc.subject	Function Approximation	en
dc.subject	Fuzzy Model	en
dc.subject	neuro fuzzy	en
dc.subject	Reinforcement Learning	en
dc.subject	takagi sugeno kang	en
dc.subject.classification	Computer Science, Artificial Intelligence	en
dc.subject.other	Algorithms	en
dc.subject.other	Computational complexity	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Learning systems	en
dc.subject.other	Neural networks	en
dc.subject.other	Optimal systems	en
dc.subject.other	Parameter estimation	en
dc.subject.other	Reliability	en
dc.subject.other	Functional reasoning methods	en
dc.subject.other	Fuzzy ART concepts	en
dc.subject.other	Mean reward	en
dc.subject.other	Value functions	en
dc.subject.other	Fuzzy control	en
dc.title	ART-based neuro-fuzzy modelling applied to reinforcement learning	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1007/978-3-540-45226-3_4	en
heal.identifier.secondary	http://dx.doi.org/10.1007/978-3-540-45226-3_4	en
heal.language	English	en
heal.publicationDate	2003	en
heal.abstract	The mountain car problem is a well-known task, often used for testing reinforcement learning algorithms. It is a problem with real valued state variables, which means that some kind of function approximation is required. In this paper, three reinforcement learning architectures are compared on the mountain car problem. Comparison results are presented, indicating the potentials of the actor-only approach. The function approximation modules used are based on NeuroFAST (Neuro-Fuzzy ART-Based Structure and Parameter Learning TSK Model). NeuroFAST is a neuro-fuzzy modelling algorithm, with well-proven function approximation capabilities, and features the functional reasoning method (the Takagi-Sugeno-Kang fuzzy model), Fuzzy ART concepts and specific techniques.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)	en
heal.bookName	LECTURE NOTES IN ARTIFICIAL INTELLIGENCE	en
dc.identifier.doi	10.1007/978-3-540-45226-3_4	en
dc.identifier.isi	ISI:000186518100004	en
dc.identifier.volume	2774 PART 2	en
dc.identifier.spage	22	en
dc.identifier.epage	29	en