Bandit problems in networks: Asymptotically efficient distributed allocation rules

Proceedings of the IEEE Conference on Decision and Control

Volumn , Issue , 2011, Pages 1771-1778

  Kar, Soummya ^a   Poor, H Vincent ^a   Cui, Shuguang ^b  

^a Princeton University   (United States)

^b Department of Electrical and Computer Engineering   (United States)

Author keywords

Asymptotically Efficient; Distributed Allocation Rules; Networked Bandit Problems; Partially Observable Rewards

Indexed keywords

MULTI AGENT SYSTEMS;

ALLOCATION RULE; ASYMPTOTICALLY EFFICIENT; BANDIT PROBLEMS; DISTRIBUTED ALLOCATION; OPTIMAL REGRET; PARTIALLY OBSERVABLE REWARDS; SINGLE-AGENT; UNOBSERVABLE;

PROBABILITY;

EID: 84860652887     PISSN: 07431546     EISSN: 25762370     Source Type: Conference Proceeding    
DOI: 10.1109/CDC.2011.6160719     Document Type: Conference Paper

References (10)

1. T. L. Lai, "Some thoughts on stochastic adaptive control," in Proc. of 23rd IEEE Conf. Decision Contr., Las Vegas, NV, Dec. 1984, pp. 51-56.
2. T. L. Lai and H. Robbins, "Asymptotically efficient adaptive allocation rules," Advances in Applied Mathematics, vol. 6, pp. 4-22, 1985.
3. V. Anantharam, P. Varaiya, and J. Walrand, "Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays -part I: I.I.D. rewards," IEEE Transactions on Automatic Control, vol. 32, no. 11, pp. 968-976, November 1987.
4. K. Liu and Q. Zhao, "Distributed learning in multi-armed bandit with multiple players," IEEE Transactions on Signal Processing, vol. 58, no. 11, pp. 5667-5681, November 2010.
5. A. Anandkumar, N. Michael, A. K. Tang, and A. Swami, "Distributed algorithms for learning and cognitive medium access with logarithmic regret," To appear in the IEEE Journal of Selected Areas in Communications - Issue on Advances in Cognitive Radio Networking and Communications, dec. 2009, revised May 2010.
6. C. C. Wang, S. R. Kulkarni, and H. V. Poor, "Bandit problems with side observations," IEEE Transactions on Automatic Control, vol. 50, no. 3, pp. 338-355, March 2005.
7. -, "Arbitrary side observations in bandit problem," Advances in Applied Mathematics, vol. 34, no. 2, pp. 903-938, May 2005.
8. F. R. K. Chung, Spectral Graph Theory. Providence, RI : American Mathematical Society, 1997.
9. B. Bollobas, Modern Graph Theory. New York: Springer Verlag, 1998.
10. S. Kar, J. M. F. Moura, and K. Ramanan, "Distributed parameter estimation in sensor networks: nonlinear observation models and imperfect communication," August 2008, submitted to the IEEE Transactions on Information Theory, 51 pages. [Online]. Available: http://arxiv.org/abs/0809. 0009