Hedging the Drift: Learning to Optimize Under Nonstationarity
<jats:p> We introduce data-driven decision-making algorithms that achieve state-of-the-art dynamic regret bounds for a collection of nonstationary stochastic bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and traffic network routing in c...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute for Operations Research and the Management Sciences (INFORMS)
2023
|
| Online Access: | https://hdl.handle.net/1721.1/148652 |