Matthew W. Robards, Peter Sunehag. Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control. In Scott Sanner, Marcus Hutter, editors, Recent Advances in Reinforcement Learning - 9th European Workshop, EWRL 2011, Athens, Greece, September 9-11, 2011, Revised Selected Papers. Volume 7188 of Lecture Notes in Computer Science, pages 30-41, Springer, 2011. [doi]