IEEE - Institute of Electrical and Electronics Engineers, Inc. - Learning task decomposition and exploration shaping for reinforcement learning agents

2008 IEEE International Conference on Systems, Man and Cybernetics (SMC 2008)

Author(s): P. Djurdjevic ; M. Huber
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 October 2008
Conference Location: Singapore, Singapore
Conference Date: 12 October 2008
Page(s): 365 - 372
ISBN (CD): 978-1-4244-2384-2
ISBN (Paper): 978-1-4244-2383-5
ISSN (Paper): 1062-922X
DOI: 10.1109/ICSMC.2008.4811303
Regular:

For situated reinforcement learning agents to succeed in complex real world environments they have to be able to efficiently acquire and reuse control knowledge in order to accomplish new tasks... View More

Advertisement