BibTeX
@inproceedings{icann2007, author = "Wierstra, D. and Foerster, A. and Peters, J. and Schmidhuber, J.", year = "2007", title = "Solving Deep Memory POMDPs with Recurrent Policy Gradients", booktitle = "Proceedings of the International Conference on Artificial Neural Networks (ICANN)", key = "policy gradients, reinforcement learning", URL = "https://www.ias.informatik.tu-darmstadt.de/uploads/Publications/Publications/icann2007.pdf", crossref = "p10132" }