Parameter-exploring policy gradientsFrank Sehnke, Jürgen Schmidhuber, Jan Peters et al.|Neural Networks|2009Cited by 246
Solving Deep Memory POMDPs with Recurrent Policy GradientsDaan Wierstra, Jürgen Schmidhuber, A. Foerster et al.|Lecture notes in computer science|2007Cited by 149
Recurrent policy gradientsDaan Wierstra, Jürgen Schmidhuber, Alexander Förster et al.|Logic Journal of IGPL|2009Cited by 105
Policy Gradients with Parameter-Based Exploration for ControlFrank Sehnke, Jürgen Schmidhuber, Christian Osendorfer et al.|Lecture notes in computer science|2008Cited by 60
Fitness Expectation MaximizationDaan Wierstra, Jürgen Schmidhuber, Jan Peters et al.|Lecture notes in computer science|2008Cited by 25