@article{policyoptimizationwithpenalizedpoint,
  title = {Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization},
  author = {Xiangxiang Chu},
  year = {2018},
  eprint = {1807.00442},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1807.00442v4},
}