@inproceedings{optimisticpolicyoptimizationwithbandit, title = {Optimistic Policy Optimization with Bandit Feedback}, author = {Yonathan Efroni and Lior Shani and Aviv Rosenberg and Shie Mannor}, year = {2020}, booktitle = {ICML 2020 1}, eprint = {2002.08243}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2002.08243v2}, }