Rising Rested MAB with Linear Drift
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909451235098624 |
|---|---|
| author | Amichay, Omer Mansour, Yishay |
| author_facet | Amichay, Omer Mansour, Yishay |
| contents | We consider non-stationary multi-arm bandit (MAB) where the expected reward of each action follows a linear function of the number of times we executed the action. Our main result is a tight regret bound of $\tildeΘ(T^{4/5}K^{3/5})$, by providing both upper and lower bounds. We extend our results to derive instance dependent regret bounds, which depend on the unknown parametrization of the linear drift of the rewards. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04403 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rising Rested MAB with Linear Drift Amichay, Omer Mansour, Yishay Machine Learning We consider non-stationary multi-arm bandit (MAB) where the expected reward of each action follows a linear function of the number of times we executed the action. Our main result is a tight regret bound of $\tildeΘ(T^{4/5}K^{3/5})$, by providing both upper and lower bounds. We extend our results to derive instance dependent regret bounds, which depend on the unknown parametrization of the linear drift of the rewards. |
| title | Rising Rested MAB with Linear Drift |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.04403 |