Simulation-based optimization of Markov reward processes

@article{Marbach2001SimulationbasedOO,
  title={Simulation-based optimization of Markov reward processes},
  author={Peter Marbach and John N. Tsitsiklis},
  journal={IEEE Trans. Automat. Contr.},
  year={2001},
  volume={46},
  pages={191-209}
}
We propose a simulation based algorithm for optimizing the average reward in a Markov Reward Process that depends on a set of parameters As a special case the method applies to Markov Decision Processes where optimization takes place within a parametrized set of policies The algorithm involves the simulation of a single sample path and can be implemented on line A convergence result with probability is provided This research was supported by contracts with Siemens AG Munich Germany and Alcatel… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 197 CITATIONS, ESTIMATED 24% COVERAGE

FILTER CITATIONS BY YEAR

1999
2019

CITATION STATISTICS

  • 33 Highly Influenced Citations

  • Averaged 9 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 16 REFERENCES

Simulation- Based Optimization of Markov Reward Processes

  • P. Marbach, J. N. Tsitsiklis
  • Lab. for Info. and Decision Systems Report LIDS…
  • 1998
1 Excerpt

Perturbation Real- ization

  • X. R. Cao, H. F. Chen
  • Potentials, and Sensitivity Analysis of Markov…
  • 1997
2 Excerpts

and M

  • T. Jaakkola, S. P. Singh
  • I. Jordan, \Re- inforcement Learning Algorithm…
  • 1995
3 Excerpts

Ramadage, \Stochastic Optimization of Regenerative Systems Using In nites- imal Perturbation Analysis,

  • P.J.E.K.P. Chong
  • IEEE Trans. on Auto- matic Control,
  • 1994
2 Excerpts

Similar Papers

Loading similar papers…