BibTeX
@inproceedings{tosatto2020, author = "Tosatto, S. and Carvalho, J. and Abdulsamad, H. and Peters, J.", year = "2020", title = "A Nonparametric Off-Policy Policy Gradient", booktitle = "Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS)", key = "nonparametric, policy gradient, off policy, reinforcement learning", URL = "https://www.ias.informatik.tu-darmstadt.de/uploads/Team/SamueleTosatto/tosatto2020.pdf", crossref = "p11316" }