@misc{schulman2015trust,
  title={Trust Region Policy Optimization},
  author={John Schulman and Sergey Levine and Philipp Moritz and Michael I. Jordan and Pieter Abbeel},
  year={2015},
  eprint={1502.05477},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/1502.05477}
}