Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds

@article{Petrik2012ApproximateDP,
  title={Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds},
  author={Marek Petrik},
  journal={CoRR},
  year={2012},
  volume={abs/1205.1782}
}
Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods— distributionally robust ADP—that address the curse of dimensionality by minimizing a pessimistic bound on the policy loss. This approach turns ADP into an optimization problem, for which we derive new mathematical program formulations and analyze its properties. DRADP improves on the theoretical guarantees of existing… CONTINUE READING
3 Citations
16 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Approximate dynamic programming by minimizing distributionally robust bounds

  • Petrik, Marek
  • Arxiv
  • 2012

Robust Optimization

  • Ben-Tal, Aharon, Ghaoui, Laurent El, Nemirovski, Arkadi
  • 2009
1 Excerpt

New Representations and Approximations for Sequential Decision Making

  • Wang, Tao
  • PhD thesis, University of Alberta,
  • 2007

Similar Papers

Loading similar papers…