Optimal output-feedback control of unknown continuous-time linear systems using off-policy reinforcement learning. Modares, H., Lewis, F. L., & Jiang, Z. IEEE Trans. Cybern., 46(11):2401–2410, September, 2016.
Paper doi bibtex @Article{SCC.Modares.Lewis.ea2016,
author = {Modares, Hamidreza and Lewis, Frank L. and Jiang, Zhong-Ping},
title = {Optimal output-feedback control of unknown continuous-time linear systems using off-policy reinforcement learning},
journal = {IEEE Trans. Cybern.},
year = {2016},
volume = {46},
number = {11},
pages = {2401--2410},
month = sep,
doi = {10.1109/TCYB.2015.2477810},
file = {SCC.Modares.Lewis.ea2016.pdf:SCC.Modares.Lewis.ea2016.pdf:PDF},
keywords = {ADP, Output-Feedback},
owner = {Kamalapurkar},
timestamp = {2017-12-29},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7574391},
}