Open AccessA Reinforcement Learning Algorithm Using Multi-Layer Artificial Neural Networks for Semi-Markov Decision Problems
Author(s) -
Mustafa Ahmet Beyazıt Ocaktan,
Ufuk Kula
Publication year - 2013
Publication title -
dergipark (istanbul university)
Language(s) - English
DOI - 10.16984/saufbed.75737
Subject(s) - reinforcement learning , artificial intelligence , artificial neural network , computer science , markov decision process , machine learning , layer (electronics) , markov process , mathematics , materials science , statistics , composite material