@article{optimizationapproachesforcounterfactual, title = {Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline Evaluation}, author = {Houssam Zenati and Alberto Bietti and Matthieu Martin and Eustache Diemert and Pierre Gaillard and Julien Mairal}, year = {2020}, eprint = {2004.11722}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2004.11722v6}, }