Andreas Witsch, Roland Reichle, Kurt Geihs, Sascha Lange, Martin Riedmiller. Enhancing the episodic natural actor-critic algorithm by a regularisation term to stabilize learning of control structures. In 2011 IEEE Symposium on Adaptive Dynamic Programming And Reinforcement Learning, ADPRL 2011, Paris, France, April 12-14, 2011. pages 156-163, IEEE, 2011. [doi]
Abstract is missing.