Abstract
We consider the restless Markov bandit problem, in which the state of each arm evolves according to a Markov process independently of the learner’s actions. We suggest an algorithm that after T steps achieves \(\tilde{O}(\sqrt{T})\) regret with respect to the best policy that knows the distributions of all arms. No assumptions on the Markov chains are made except that they are irreducible. In addition, we show that index-based policies are necessarily suboptimal for the considered problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Adv. in Appl. Math. 6, 4–22 (1985)
Akyildiz, I.F., Lee, W.Y., Vuran, M.C., Mohanty, S.: A survey on spectrum management in cognitive radio networks. IEEE Commun. Mag. 46(4), 40–48 (2008)
Anantharam, V., Varaiya, P., Walrand, J.: Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays, part II: Markovian rewards. IEEE Trans. Automat. Control 32(11), 977–982 (1987)
Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32, 48–77 (2002)
Audibert, J.-Y., Bubeck, S.: Minimax policies for adversarial and stochastic bandits. In: COLT 2009. Proc. 22nd Annual Conf. on Learning Theory, pp. 217–226 (2009)
Jaksch, T., Ortner, R., Auer, P.: Near-optimal regret bounds for reinforcement learning. J. Mach. Learn. Res. 11, 1563–1600 (2010)
Bartlett, P.L., Tewari, A.: REGAL: A regularization based algorithm for reinforcement learning in weakly communicating MDPs. In: Proc. 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009, pp. 35–42. AUAI Press (2009)
Tekin, C., Liu, M.: Adaptive learning of uncontrolled restless bandits with logarithmic regret. In: 49th Annual Allerton Conference, pp. 983–990. IEEE (2011)
Filippi, S., Cappe, O., Garivier, A.: Optimally sensing a single channel without prior information: The tiling algorithm and regret bounds. IEEE J. Sel. Topics Signal Process. 5(1), 68–76 (2011)
Levin, D.A., Peres, Y., Wilmer, E.L.: Markov chains and mixing times. American Mathematical Society (2006)
Gittins, J.C.: Bandit processes and dynamic allocation indices. J. R. Stat. Soc. Ser. B Stat. Methodol. 41(2), 148–177 (1979)
Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multi-armed bandit problem. Mach. Learn. 47, 235–256 (2002)
Whittle, P.: Restless bandits: Activity allocation in a changing world. J. Appl. Probab. 25, 287–298 (1988)
Ortner, R.: Pseudometrics for State Aggregation in Average Reward Markov Decision Processes. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds.) ALT 2007. LNCS (LNAI), vol. 4754, pp. 373–387. Springer, Heidelberg (2007)
Aldous, D.J., Fill, J.: Reversible Markov Chains and Random Walks on Graphs (in preparation), http://www.stat.berkeley.edu/~aldous/RWG/book.html
Aldous, D.J.: Threshold limits for cover times. J. Theoret. Probab. 4, 197–211 (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ortner, R., Ryabko, D., Auer, P., Munos, R. (2012). Regret Bounds for Restless Markov Bandits. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2012. Lecture Notes in Computer Science(), vol 7568. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34106-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-34106-9_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34105-2
Online ISBN: 978-3-642-34106-9
eBook Packages: Computer ScienceComputer Science (R0)