The knowledge gradient algorithm for online subset selection

2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL 2009 - Proceedings

Volumn , Issue , 2009, Pages 137-144

  Ryzhov, Ilya O ^a   Powell, Warren ^a  

^a Princeton University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION RULES; EXPERIMENTAL EVIDENCE; GRADIENT ALGORITHM; LOOK-AHEAD; MULTI-ARMED BANDIT PROBLEM; ONLINE LEARNING; SUBSET SELECTION;

DYNAMIC PROGRAMMING; EDUCATION; INTERNET; REINFORCEMENT; REINFORCEMENT LEARNING; SYSTEMS ENGINEERING;

SET THEORY;

EID: 67650505320     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ADPRL.2009.4927537     Document Type: Conference Paper

References (18)

1. D. Bertsimas and J. Nino-Mora, "Restless bandits, linear programing relaxations, and a primal-dual index heuristic," Operations Research, Vol. 48, no. 1, 80-90, 2000. (Pubitemid 30930252)
2. S. Chick, J. Branke and C. Schmidt, "New myopic sequential sampling procedures," 2007, submitted for publication.
3. M.H. De Groot, Optimal Statistical Decisions. John Wiley and Sons, 1970.
4. M.O. Duff, 'Q-learning for bandit problems, " Technical report, Dept. of Comp. Sci., University of Massachusetts, Amherst, MA, 1995.
5. P.I. Frazier, W.B. Powell and S. Dayanik, "A knowledge-gradient policy for sequential information collection," SIAM J. on Control and Optimization, 2008, to appear.
6. P.I. Frazier, W.B. Powell and S. Dayanik, "The knowledge gradient policy for correlated normal rewards," 2008, submitted for publication.
7. J. Gittins, Multi-Armed Bandit Allocation Indices. John Wiley and Sons, New York, 1989.
8. S. Gupta and K. Miescke, "Bayesian look ahead one stage sampling allocations for selecting the largest normal mean," Statistical Papers, Vol. 35, 169-177, 1994.
9. S. Gupta and K. Miescke, "Bayesian look ahead one stage sampling allocations for selection of the best population," Journal of Statistical Planning and Inference, Vol. 54, no. 2, 229-244, 1996. (Pubitemid 126161097)
10. W.C. Horrace, J.T. Marchand and T.M. Smeeding, "Ranking inequality: Applications of multivariate subset selection," Journal of Economic Inequality, Vol. 6, no. 1, 5-32, 2008.
11. L.P. Kaelbling, Learning in Embedded Systems. MIT Press, Cambridge, MA, 1993.
12. M. Katehakis and A.F. Veinott Jr., "The Multi-Armed Bandit Problem: Decomposition And Computation," Math. of OR, Vol. 12, no. 2, pp. 262-268, 1987. (Pubitemid 17603261)
13. A.J. Miller, Subset Selection in Regression, 2nd ed. CRC Press, 2002.
14. S. Pandey, D. Chakrabarti and D. Agarwal, "Multi-armed bandit problems with dependent arms, " Proceedings of the 24th International Conference on Machine Learning, 721-728. (Pubitemid 47275130)
15. W.B. Powell, Approximate Dynamic Programming: Solving the curses of dimensionality. John Wiley and Sons, New York, 2007.
16. I.O. Ryzhov, W.B. Powell and P.I. Frazier, "The knowledge gradient algorithm for a general class of online learning problems," 2008, submitted for publication.
17. J. Vermorel and M. Mohri, "Multi-armed bandit algorithms and empirical evaluation," Proceedings of the 16th European Conference on Machine Learning, 437-448, 2005.
18. Y. Yao, "Some results on the Gittins index for a normal reward process," in: H. Ho, C. Ing & T. Lai, eds., Time Series and Related Topics: In Memory of Ching-Zong Wei, Institute of Mathematical Statistics, Beachwood, OH, USA, 284-294, 2006.