Identyfikatory
Warianty tytułu
Języki publikacji
Abstrakty
In this paper an application of decision rules to function representation in reinforcement learning is described. Rules are generated incrementally by method based on rough set theory from instances recorded in state-action-Q-value memory. Simulation experiment investigating the performance of the system and results achieved are reported.
Słowa kluczowe
Czasopismo
Rocznik
Tom
Strony
989--996
Opis fizyczny
Bibliogr. 12 poz.,
Twórcy
autor
- Institute of Computing Science, Poznań University of Technology, Piotrowo 3a, 60-965 Poznań, michalsk@sol.put.poznan.pl
Bibliografia
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-article-BAT2-0001-0078