@article{5904, title = {Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning}, author = {Morimura, T. and Uchibe, E. and Yoshimoto, J. and Peters, J. and Doya, K.}, journal = {Neural Computation}, volume = {22}, number = {2}, pages = {342-376}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, month = feb, year = {2010}, doi = {10.1162/neco.2009.12-08-922}, month_numeric = {2} }