IEEE - Institute of Electrical and Electronics Engineers, Inc. - Learning parameterized policies for Markov decision processes through demonstrations

2016 IEEE 55th Conference on Decision and Control (CDC)

Author(s): Manjesh K. Hanawal ; Hao Liu ; Henghui Zhu ; Ioannis C. Paschalidis
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 December 2016
Conference Location: Las Vegas, NV, USA
Conference Date: 12 December 2016
Page(s): 7,087 - 7,092
ISBN (Electronic): 978-1-5090-1837-6
ISBN (DVD): 978-1-5090-1844-4
DOI: 10.1109/CDC.2016.7799361
Regular:

We consider the problem of learning a policy used by an agent in a Markov decision process using state-action samples. We focus on a class of parameterized policies and use... View More

Advertisement