@inproceedings{wassersteinreinforcementlearning, title = {Learning to Score Behaviors for Guided Policy Optimization}, author = {Aldo Pacchiano and Jack Parker-Holder and Yunhao Tang and Anna Choromanska and Krzysztof Choromanski and Michael. I. Jordan}, year = {2019}, booktitle = {ICML 2020 1}, eprint = {1906.04349}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1906.04349v4}, }