@conference{BelPet18,
  title = {Mean squared advantage minimization as a consequence of entropic policy improvement regularization},
  booktitle = {European Workshop on Reinforcement Learning (EWRL)},
  month = oct,
  year = {2018},
  author = {Belousov, B. and Peters, J.},
  url = {https://ewrl.files.wordpress.com/2018/09/ewrl_14_2018_paper_33.pdf},
  month_numeric = {10}
}