An asymptotically optimal strategy for constrained multi-armed bandit problems


This note considers the model of “constrained multi-armed bandit” (CMAB) that generalizes that of the classical stochastic MAB by adding a feasibility constraint for each action. The feasibility is in fact another (conflicting) objective that should be kept in order for a playing-strategy to achieve the optimality of the main objective. While the stochastic MAB model is a special case of the Markov decision process (MDP) model, the CMAB model is a special case of the constrained MDP model. For the asymptotic optimality measured by the probability of choosing an optimal feasible arm over infinite horizon, we show that the optimality is achievable by a simple strategy extended from the \(\epsilon _t\)-greedy strategy used for unconstrained MAB problems. We provide a finite-time lower bound on the probability of correct selection of an optimal near-feasible arm that holds for all time steps. Under some conditions, the bound approaches one as time t goes to infinity. A particular example sequence of \(\{\epsilon _t\}\) having the asymptotic convergence rate in the order of \((1-\frac{1}{t})^4\) that holds from a sufficiently large t is also discussed.

This is a preview of subscription content, log in to check access.


  1. Achab M, Clemencon S, Garivier A (2018) Profitable bandits. In: Proceedings of the 10th Asian conference on machine learning, vol 95, pp 694–709

  2. Altman E (1998) Constrained Markov decision processes. Chapman & Hall, London

    Google Scholar 

  3. Audibert J-Y, Bubeck S, Munos R (2010) Best arm identification in multi-armed bandits. In Proceedings of the 23rd international conference on learning theory (COLT)

  4. Auer P, Cesa-Bianchi N, Fisher P (2002) Finite-time analysis of the multiarmed bandit problem. Mach Learn 47:235–256

    Article  Google Scholar 

  5. Bather J (1980) Randomized allocation of treatments in sequential trials. Adv Appl Probab 12(1):174–182

    MathSciNet  Article  Google Scholar 

  6. Berry D, Fristedt B (1985) Bandit problems: sequential allocation of experiments. Chapman & Hall, London

    Google Scholar 

  7. Browne CB, Powley E, Whitehouse D, Lucas SM, Cowling PI, Rohlfshagen P, Tavener S, Perez D, Samothrakis S, Colton S (2012) A survey of Monte Carlo tree search methods. IEEE Trans Comput Intell AI Games 4(1):1–43

    Article  Google Scholar 

  8. Bubeck S, Munos R, Stoltz G (2011) Pure exploration in finitely armed and continuous armed bandits. Theor Comput Sci 412:1832–1852

    MathSciNet  Article  Google Scholar 

  9. Cesa-Bianchi N, Lugosi G (2006) Prediction, learning, and games. Cambridge University Press, Cambridge

    Google Scholar 

  10. Denardo EV, Feinberg EA, Rothblum UG (2013) The multi-armed bandit, with constraints. Ann Oper Res 208(1):37–62

    MathSciNet  Article  Google Scholar 

  11. Ding W, Qin T, Zhang XD, Liu TY (2013) Multi-armed bandit with budget constraint and variable costs. In: Proceedings of the 27th AAAI conference on artificial intelligence, pp 232–238

  12. Gittins J, Glazebrook K, Weber R (2011) Multi-armed bandit allocation indices. Wiley, Hoboken

    Google Scholar 

  13. Hoeffding W (1963) Probability inequalities for sums of bounded random variables. J Am Stat Assoc 58:13–30

    MathSciNet  Article  Google Scholar 

  14. Hunter SR, Pasupathy R (2013) Optimal sampling laws for stochastically constrained simulation optimization on finite sets. INFORMS J Comput 25(3):527–542

    MathSciNet  Article  Google Scholar 

  15. Kuleshov V, Precup D (2014) Algorithms for the multi-armed bandit problem. arXiv:1402.6028

  16. Lai T, Robbins H (1985) Asymptotically efficient adaptive allocation rules. Adv Appl Math 6:4–22

    MathSciNet  Article  Google Scholar 

  17. Lan G, Zhou Z (2016) Algorithms for stochastic optimization with expectation constraints. arXiv:1604.03887

  18. Locatelli A, Gutzeit M, Carpentier A (2016) An optimal algorithm for the thresholding bandit problem. In: Proceedings of the 33rd international conference on machine learning, pp 1690–1698

  19. Mahajan A, Teneketzis D (2007) Multi-armed bandit problems. In: Hero AO, Castanon DA, Cochran D, Kastella K (eds) Foundations and applications of sensor management. Springer, Boston

    Google Scholar 

  20. Park C, Kim S (2015) Penalty function with memory for discrete optimization via simulation with stochastic constraints. Oper Res 63(5):1195–1212

    MathSciNet  Article  Google Scholar 

  21. Pasupathy R, Hunter SR, Pujowidianto NA, Lee LH, Chen C (2014) Stochastically constrained ranking and selection via SCORE. ACM Trans Modeling Comput Simul 25, Article 1

  22. Robbins H (1952) Some aspects of the sequential design of experiments. Bull Am Math Soc 58:527–535

    MathSciNet  Article  Google Scholar 

  23. Santner T, Tamhane A (1984) Design of experiments: ranking and selection. CRC Press, Boca Raton

    Google Scholar 

  24. Spall JC (2003) Introduction to stochastic search and optimization: estimation, simulation, and control. Wiley, Hoboken

    Google Scholar 

  25. Tekin C, Liu M (2013) Online learning methods for networking. Found Trends Netw 8(4):281–409

    Article  Google Scholar 

  26. Uspensky JV (1937) Introduction to mathematical probability. McGraw-Hill, London

    Google Scholar 

  27. Vermorel J, Mohri M (2005) Multi-armed bandit algorithms and empirical evaluation. In: Gama J, Camacho R, Brazdil PB, Jorge AM, Torgo L (eds) Machine learning: ECML 2005, vol 3720. Lecture notes in computer science. Springer, Berlin, pp 437–448

    Google Scholar 

  28. Wang W, Ahmed S (2008) Sample average approximation of expected value constrained stochastic systems. Oper Res Lett 36:515–519

    MathSciNet  Article  Google Scholar 

  29. Watanabe R, Komiyama J, Nakamura A, Kudo M (2017) KL-UCB-based policy for budgeted multi-armed bandits with stochastic action costs. IEICE Trans Fundam Electron Commun Comput Sci E100–A(11):2470–2486

    Article  Google Scholar 

  30. Zhou DP, Tomlin CJ (2018) Budget-constrained multi-armed bandits with multiple plays. In: Proceedings of the 32nd AAAI conference on artificial intelligence, pp 4572–4579

Download references

Author information



Corresponding author

Correspondence to Hyeong Soo Chang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Chang, H.S. An asymptotically optimal strategy for constrained multi-armed bandit problems. Math Meth Oper Res 91, 545–557 (2020).

Download citation


  • Multi-armed bandit
  • Constrained stochastic optimization
  • Simulation optimization
  • Constrained Markov decision process