@misc{schulman2017proximal, title={Proximal Policy Optimization Algorithms}, author={John Schulman and Filip Wolski and Prafulla Dhariwal and Alec Radford and Oleg Klimov}, year={2017}, eprint={1707.06347}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1707.06347} }