Factored Bandits
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
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).
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada. |
Antal sider | 10 |
Forlag | NIPS Proceedings |
Publikationsdato | 2018 |
Status | Udgivet - 2018 |
Begivenhed | 32nd Annual Conference on Neural Information Processing Systems - Montreal, Montreal, Canada Varighed: 2 dec. 2018 → 8 dec. 2018 Konferencens nummer: 32 https://nips.cc/Conferences/2018 |
Konference
Konference | 32nd Annual Conference on Neural Information Processing Systems |
---|---|
Nummer | 32 |
Lokation | Montreal |
Land | Canada |
By | Montreal |
Periode | 02/12/2018 → 08/12/2018 |
Internetadresse |
Navn | Advances in Neural Information Processing Systems |
---|---|
Vol/bind | 31 |
ISSN | 1049-5258 |
ID: 225479776