@article{onproximalpolicyoptimizationsheavy1, title = {On Proximal Policy Optimization's Heavy-tailed Gradients}, author = {Saurabh Garg and Joshua Zhanson and Emilio Parisotto and Adarsh Prasad and J. Zico Kolter and Zachary C. Lipton and Sivaraman Balakrishnan and Ruslan Salakhutdinov and Pradeep Ravikumar}, year = {2021}, eprint = {2102.10264}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2102.10264v2}, }