Non-randomized policies for constrained Markov decision processes

@article{Chen2007NonrandomizedPF,
  title={Non-randomized policies for constrained Markov decision processes},
  author={Richard C. Chen and Eugene A. Feinberg},
  journal={Math. Meth. of OR},
  year={2007},
  volume={66},
  pages={165-179}
}
This paper addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by nonrandomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the infinite horizon value function is also shown. A simple example illustrating an application is presented. 
9 Citations
7 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-7 of 7 references

Constrained Markov Processes and Optimal Truncated Sequential Detection,

  • R. C. Chen
  • Defence Applications of Signal Processing…
  • 2005
1 Excerpt

Non-Randomized Policies for Constrained Markov Decision Processes

  • R. T. Rockafellar, R. J-B
  • 1998

Similar Papers

Loading similar papers…