Finite horizon Markov control with one-step variance penalties

Abhijit Gosavi. Finite horizon Markov control with one-step variance penalties. In 48th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020. pages 1355-1359, IEEE, 2010. [doi]

@inproceedings{Gosavi10,
  title = {Finite horizon Markov control with one-step variance penalties},
  author = {Abhijit Gosavi},
  year = {2010},
  doi = {10.1109/ALLERTON.2010.5707071},
  url = {https://doi.org/10.1109/ALLERTON.2010.5707071},
  researchr = {https://researchr.org/publication/Gosavi10},
  cites = {0},
  citedby = {0},
  pages = {1355-1359},
  booktitle = {48th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020},
  publisher = {IEEE},
  isbn = {978-1-4244-8216-0},
}