Learning to Optimize Under Non-Stationarity
© 2019 by the author(s). We introduce algorithms that achieve state-of-the-art dynamic regret bounds for non-stationary linear stochastic bandit setting. It captures natural applications such as dynamic pricing and ads allocation in a changing environment. We show how the difficulty posed by the non...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV,
2021-11-02T12:19:41Z.
|
| Subjects: | |
| Online Access: | Get fulltext |