Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs

Prashanth and Ghavamzadeh. "Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs." Machine Learning, 2016. doi:10.1007/S10994-016-5569-5

[Prashanth and Ghavamzadeh. "Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs." Machine Learning, 2016.](https://mlanthology.org/mlj/2016/a2016mlj-varianceconstrained/) doi:10.1007/S10994-016-5569-5

@article{a2016mlj-varianceconstrained,
  title     = {{Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPs}},
  author    = {Prashanth, L. A. and Ghavamzadeh, Mohammad},
  journal   = {Machine Learning},
  year      = {2016},
  pages     = {367-417},
  doi       = {10.1007/S10994-016-5569-5},
  volume    = {105},
  url       = {https://mlanthology.org/mlj/2016/a2016mlj-varianceconstrained/}
}