@inproceedings{Peters_PIISADPRL_2007, author = "Peters, J. and Schaal, S.", year = "2007", title = "Using reward-weighted regression for reinforcement learning of task space control", booktitle = "Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning", key = "reinforcement learning, cart-pole, policy gradient methods", URL = "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/ADPRL2007-Peters_[0].pdf", crossref = "p2672" }