The Community for Technology Leaders
2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS) (2018)
Paris, France
Oct 7, 2018 to Oct 9, 2018
ISSN: 2575-8454
ISBN: 978-1-5386-4230-6
pp: 309-319
ABSTRACT
We introduce a general model of bandit problems in which the expected payout of an arm is an increasing concave function of the time since it was last played. We first develop a PTAS for the underlying optimization problem of determining a reward-maximizing sequence of arm pulls. We then show how to use this PTAS in a learning setting to obtain sublinear regret.
INDEX TERMS
concave programming,
CITATION

R. Kleinberg and N. Immorlica, "Recharging Bandits," 2018 IEEE 59th Annual Symposium on Foundations of Computer Science (FOCS), Paris, France, 2019, pp. 309-319.
doi:10.1109/FOCS.2018.00037
101 ms
(Ver 3.3 (11022016))