Learning with Dynamic Programming

  title={Learning with Dynamic Programming},
  author={Peter I. Frazier},
We consider the role of dynamic programming in sequential learning problems. These problems require deciding which information to collect in order to best support later actions. Such problems are ubiquitous, appearing in simulation, global optimization, revenue management, and many other areas. Dynamic programming offers a coherent framework for understanding and solving Bayesian formulations of these problems. We present the dynamic programming formulation applied to a canonical problem… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 63 references

Knowledge-Gradient Methods for Statistical Learning

P. Frazier
PhD thesis, Princeton University. 1, 6 • 2009
View 8 Excerpts
Highly Influenced

Bandit problems

D. Bergemann, J. Valimaki
Cowles Foundation Discussion Paper 1551, Yale University. 7 • 2006
View 4 Excerpts
Highly Influenced

Multi-Armed Bandit Allocation Indices (J. C. Gittins)

SIAM Review • 1991
View 5 Excerpts
Highly Influenced

On the Theory of Dynamic Programming.

Proceedings of the National Academy of Sciences of the United States of America • 1952
View 5 Excerpts
Highly Influenced

Optimum Character of the Sequential Probability Ratio Test

A. Wald, J. Wolfowitz
The Annals of Mathematical Statistics, 19(3):326–339. 1, 9, 10 • 1948
View 6 Excerpts
Highly Influenced

Bayesian sequential change diagnosis

View 2 Excerpts
Highly Influenced

Quickest Detection

O. Hadjiliadis, H. Poor
Cambridge Univ Press. 6 • 2008
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…