Bruno C. da Silva, Andrew G. Barto. TD-DeltaPi: A Model-Free Algorithm for Efficient Exploration. In Jörg Hoffmann, Bart Selman, editors, Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada. pages 886-892, AAAI Press, 2012. [doi]
Abstract is missing.