Factored Bandits
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. Factored bandits incorporate rank-1 bandits as a special case, but significantly relax the assumptions on the form of the reward function. We provide an anytime algorithm for stochastic factored bandits and up to constants matching upper and lower regret bounds for the problem. Furthermore, we show that with a slight modification the proposed algorithm can be applied to utility based dueling bandits. We obtain an improvement in the additive terms of the regret bound compared to state of the art algorithms (the additive terms are dominating up to time horizons which are exponential in the number of arms).
Original language | English |
---|---|
Title of host publication | Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada. |
Number of pages | 10 |
Publisher | NIPS Proceedings |
Publication date | 2018 |
Publication status | Published - 2018 |
Event | 32nd Annual Conference on Neural Information Processing Systems - Montreal, Montreal, Canada Duration: 2 Dec 2018 → 8 Dec 2018 Conference number: 32 https://nips.cc/Conferences/2018 |
Conference
Conference | 32nd Annual Conference on Neural Information Processing Systems |
---|---|
Nummer | 32 |
Location | Montreal |
Land | Canada |
By | Montreal |
Periode | 02/12/2018 → 08/12/2018 |
Internetadresse |
Series | Advances in Neural Information Processing Systems |
---|---|
Volume | 31 |
ISSN | 1049-5258 |
ID: 225479776