@misc{W1771410628,
  author = {John Schulman and Sergey Levine and Philipp Moritz and Michael I. Jordan and Pieter Abbeel},
  title = {Trust Region Policy Optimization},
  year = {2015},
  howpublished = {arXiv (Cornell University)},
  doi = {https://doi.org/10.48550/arxiv.1502.05477}
}