@inproceedings{bd0b865e1ea244daa1f92d120fc6c135,
title = "Committing bandits",
abstract = "We consider a multi-armed bandit problem where there are two phases. The first phase is an experimentation phase where the decision maker is free to explore multiple options. In the second phase the decision maker has to commit to one of the arms and stick with it. Cost is incurred during both phases with a higher cost during the experimentation phase. We analyze the regret in this setup, and both propose algorithms and provide upper and lower bounds that depend on the ratio of the duration of the experimentation phase to the duration of the commitment phase. Our analysis reveals that if given the choice, it is optimal to experiment Θ(ln T ) steps and then commit, where T is the time horizon.",
author = "Loc Bui and Ramesh Johari and Shie Mannor",
year = "2011",
language = "الإنجليزيّة",
isbn = "9781618395993",
series = "Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011",
booktitle = "Advances in Neural Information Processing Systems 24",
note = "25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011 ; Conference date: 12-12-2011 Through 14-12-2011",
}