@article{5530, title = {Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning}, author = {Hachiya, H. and Akiyama, T. and Sugiyama, M. and Peters, J.}, journal = {Neural Networks}, volume = {22}, number = {10}, pages = {1399-1410}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, month = dec, year = {2009}, doi = {10.1016/j.neunet.2009.01.002}, month_numeric = {12} }