IEEE - Institute of Electrical and Electronics Engineers, Inc. - Efficient learning algorithms for episodic tasks with acyclic state spaces

2006 IEEE International Conference on Automation Science and Engineering

Author(s): S. Reveliotis ; T. Bountourelis
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 October 2006
Conference Location: Shanghai, China
Conference Date: 8 October 2006
Page(s): 411 - 418
ISBN (CD): 1-4244-0311-1
ISBN (Paper): 1-4244-0310-3
DOI: 10.1109/COASE.2006.326917
Regular:

This paper considers the problem of computing an optimal policy for a Markov decision process (MDP), under lack of complete a priori knowledge of (i) the branching probability distributions... View More

Advertisement