Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while taking the empirically best action as often as possible. A popular measure of a policy's success in addressing this dilemma is the regret, that is the loss due to the fact that the globally optimal policy is not followed all the times. One of the simplest examples of the exploration/exploitation dilemma is the multi-armed bandit problem. Lai and Robbins were the first ones to show that the regret for this problem has to grow at least logarithmically in the number of plays. Since then, policies which asymptotically achieve this regret have been devised by Lai and Robbins and many others. In this work we show that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support.
Agrawal, R. (1995). Sample mean based index policies with O(log n) regret for the multi-armed bandit problem. Advances in Applied Probability, 27, 1054–1078.
Berry, D., & Fristedt, B. (1985). Bandit problems. London: Chapman and Hall.
Burnetas, A., & Katehakis, M. (1996). Optimal adaptive policies for sequential allocation problems. Advances in Applied Mathematics, 17:2, 122–142.
Duff, M. (1995). Q-learning for bandit problems. In Proceedings of the 12th International Conference on Machine Learning (pp. 209-217).
Gittins, J. (1989). Multi-armed bandit allocation indices, Wiley-Interscience series in Systems and Optimization. New York: John Wiley and Sons.
Holland, J. (1992). Adaptation in natural and artificial systems. Cambridge: MIT Press/Bradford Books.
Ishikida, T., & Varaiya, P. (1994). Multi-armed bandit problem revisited. Journal of Optimization Theory and Applications, 83:1, 113–154.
Lai, T., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6, 4–22.
Pollard, D. (1984). Convergence of stochastic processes. Berlin: Springer.
Sutton, R., & Barto, A. (1998). Reinforcement learning, an introduction. Cambridge: MIT Press/Bradford Books.
Wilks, S. (1962). Matematical statistics. New York: John Wiley and Sons.
Yakowitz, S., & Lowe, W. (1991). Nonparametric bandit methods. Annals of Operations Research, 28, 297–312.
About this article
Cite this article
Auer, P., Cesa-Bianchi, N. & Fischer, P. Finite-time Analysis of the Multiarmed Bandit Problem. Machine Learning 47, 235–256 (2002). https://doi.org/10.1023/A:1013689704352
- bandit problems
- adaptive allocation rules
- finite horizon regret