### Abstract

The online multi-armed bandit problem and its generalizations are repeated decision making problems, where the goal is to select one of several possible decisions in every round, and incur a cost associated with the decision, in such a way that the total cost incurred over all iterations is close to the cost of the best fixed decision in hindsight. The difference in these costs is known as the regret of the algorithm. The term bandit refers to the setting where one only obtains the cost of the decision used in a given iteration and no other information. Perhaps the most general form of this problem is the non-stochastic bandit linear optimization problem, where the set of decisions is a convex set in some Euclidean space, and the cost functions are linear. Only recently an efficient algorithm attaining Õ(√T) regret was discovered in this setting. In this paper we propose a new algorithm for the bandit linear optimization problem which obtains a regret bound of Õ(√Q), where Q is the total variation in the cost functions. This regret bound, previously conjectured to hold in the full information case, shows that it is possible to incur much less regret in a slowly changing environment even in the bandit setting. Our algorithm is efficient and applies several new ideas to bandit optimization such as reservoir sampling.

Original language | English (US) |
---|---|

Title of host publication | Proceedings of the 20th Annual ACM-SIAM Symposium on Discrete Algorithms |

Publisher | Association for Computing Machinery (ACM) |

Pages | 38-47 |

Number of pages | 10 |

ISBN (Print) | 9780898716801 |

DOIs | |

State | Published - Jan 1 2009 |

Externally published | Yes |

Event | 20th Annual ACM-SIAM Symposium on Discrete Algorithms - New York, NY, United States Duration: Jan 4 2009 → Jan 6 2009 |

### Publication series

Name | Proceedings of the Annual ACM-SIAM Symposium on Discrete Algorithms |
---|

### Other

Other | 20th Annual ACM-SIAM Symposium on Discrete Algorithms |
---|---|

Country | United States |

City | New York, NY |

Period | 1/4/09 → 1/6/09 |

### All Science Journal Classification (ASJC) codes

- Software
- Mathematics(all)

## Fingerprint Dive into the research topics of 'Better algorithms for benign bandits'. Together they form a unique fingerprint.

## Cite this

*Proceedings of the 20th Annual ACM-SIAM Symposium on Discrete Algorithms*(pp. 38-47). (Proceedings of the Annual ACM-SIAM Symposium on Discrete Algorithms). Association for Computing Machinery (ACM). https://doi.org/10.1137/1.9781611973068.5