Doina Precup Richard S. Sutton Cosmin Paduraru Anna Koop Satinder P. Singh Off-policy Learning with Options and Recognizers. 2005 conf/nips/2005 NIPS http://books.nips.cc/papers/files/nips18/NIPS2005_0775.pdf db/conf/nips/nips2005.html#PrecupSPKS05