Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems

Applied Mathematics and Computation

Volumn 196, Issue 2, 2008, Pages 913-922

  Koulouriotis, D E ^a   Xanthopoulos, A ^a  

^a DEMOCRITUS UNIVERSITY OF THRACE   (Greece)

Author keywords

Action selection; Decision making agents; Exploration exploitation; Genetic algorithms; Multi armed bandit; Reinforcement learning

Indexed keywords

AD HOC NETWORKS; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; EVOLUTIONARY ALGORITHMS; GAUSSIAN DISTRIBUTION; PROBLEM SOLVING;

DECISION-MAKING AGENTS; EXPLORATION-EXPLOITATION; MULTI-ARMED BANDIT;

REINFORCEMENT LEARNING;

EID: 38649118249     PISSN: 00963003     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.amc.2007.07.043     Document Type: Article

References (17)

1. Berry D.A., and Fristedt B. Bandit Problems: Sequential Allocation of Experiments (1985), Chapman and Hall, London
2. Gittins J.C. Multi-armed Bandit Allocation Indices (1989), Wiley, New York
3. Varaiya P.P., Walrand J.C., and Buyukkoc C. Extensions of the multi armed bandit problem: the discounted case. IEEE Transactions on Automated Control 30 5 (1985) 426-439
4. Kaspi H., and Mandelbaum A. Multi-armed bandits in discrete and continuous time. Annals of Applied Probability 8 4 (1998) 1270-1290
5. Banks J.S., and Sundaram R.K. Switching costs and the Gittins index. Econometrica 62 (1994) 687-694
6. Jun T. A survey on the bandit problem with switching costs. De Economist 152 (2004) 513-541
7. P. Auer, N. Cesa-Bianchi, Y. Freund, R.E. Schapire, Gambling in a rigged Casino: the adversarial multi-armed bandit problem, in: Proceedings of the 36th Annual Symposium on Foundations of Computer Science, 1995, pp. 322-331.
8. Leloup B., and Deveaux L. Dynamic pricing on the Internet: theory and simulations. Electronic Commerce Research 1 (2001) 265-276
9. Valsecchi I. Job assignment and bandit problems. International Journal of Manpower 24 7 (2003) 844-866
10. Azoulay-Schwartz R., Kraus S., and Wilkenfeld J. Exploitation vs. exploration: choosing a supplier in an environment of incomplete information. Decision Support Systems 38 (2004) 1-18
11. McCall B.P., and McCall J.J. Systematic search, belated information and the Gittins' index. Economics Letters 8 (1981) 327-333
12. Chulkov D.V., and Desai M.S. Information technology project failures. Applying the bandit problem to evaluate managerial decision making. Information Management and Computer Security 13 2 (2005) 135-143
13. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press, Cambridge, MA
14. Kaelbling L.P., Littman M.L., and Moore A.W. Reinforcement learning: a survey. Journal of Artificial Intelligence Research 4 (1996) 237-285
15. D. Thierens, An adaptive pursuit strategy for allocating operator probabilities, in: Proceedings of the Genetic and Evolutionary Computing Conference (GECCO 2005), 2005, pp. 1539-1546.
16. Fogel D.B., and Beyer H.G. Do evolutionary processes minimize expected losses?. Journal of Theoretic Biology 207 (2000) 117-123
17. Thathachar M.A.L., and Sastry P.S. A class of rapidly converging algorithms for learning automata. IEEE Transactions on Systems, Man and Cybernetics SMC-15 (1985) 168-175