@online{huangndproximal,
  author       = {Huang, Xuanqiang Angelo},
  title        = {Proximal Polixy Optimization},
  organization = {Xuanqiang Angelo Huang's Blog},
  url          = {https://flecart.github.io/notes/proximal-polixy-optimization/},
  langid       = {english},
  abstract     = {This document is DEPRECATED, please see RL Function Approximation . This documents attempts to briefly present the algorithm and some experiments found online about it. The following repo seems to be a good resource: here . Usually, PPO is explained as an actor critic framework .}
}