Approximately optimal linear strategies for static teams with ‘big’ non-Gaussian noise

@article{Kulkarni2015ApproximatelyOL,
  title={Approximately optimal linear strategies for static teams with ‘big’ non-Gaussian noise},
  author={Ankur A. Kulkarni},
  journal={2015 54th IEEE Conference on Decision and Control (CDC)},
  year={2015},
  pages={7177-7182}
}
We study stochastic team problems with static information structure where we assume controllers have linear information and quadratic cost but allow the noise to be from a non-Gaussian class. When the noise is Gaussian, it is well known that these problems admit a linear optimal controller. We show that if the noise has a log-concave density, then for `most' problems of this kind, linear strategies are approximately optimal. The quality of the approximation improves as length of the noise… CONTINUE READING