Tetsuro Morimura Eiji Uchibe Junichiro Yoshimoto Kenji Doya A New Natural Policy Gradient by Stationary Distribution Metric. 82-97 2008 ECML/PKDD (2) http://dx.doi.org/10.1007/978-3-540-87481-2_6 conf/pkdd/2008-2 db/conf/pkdd/pkdd2008-2.html#MorimuraUYD08