@article{Tosatto_ITPAMI_inpress, author = "Tosatto, S. and Carvalho, J. and Peters, J.", year = "in press", title = "Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient", booktitle = "IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)", URL = "https://ieeexplore.ieee.org/document/9449972", crossref = "p11436" }