Bayesian Regret Minimization in Offline Bandits
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913414964576256 |
|---|---|
| author | Petrik, Marek Tennenholtz, Guy Ghavamzadeh, Mohammad |
| author_facet | Petrik, Marek Tennenholtz, Guy Ghavamzadeh, Mohammad |
| contents | We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance on LCB is inherently flawed in this setting and propose a new algorithm that directly minimizes upper bounds on the Bayesian regret using efficient conic optimization solvers. Our bounds build heavily on new connections to monetary risk measures. Proving a matching lower bound, we show that our upper bounds are tight, and by minimizing them we are guaranteed to outperform the LCB approach. Our numerical results on synthetic domains confirm that our approach is superior to LCB. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_01237 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Bayesian Regret Minimization in Offline Bandits Petrik, Marek Tennenholtz, Guy Ghavamzadeh, Mohammad Machine Learning We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance on LCB is inherently flawed in this setting and propose a new algorithm that directly minimizes upper bounds on the Bayesian regret using efficient conic optimization solvers. Our bounds build heavily on new connections to monetary risk measures. Proving a matching lower bound, we show that our upper bounds are tight, and by minimizing them we are guaranteed to outperform the LCB approach. Our numerical results on synthetic domains confirm that our approach is superior to LCB. |
| title | Bayesian Regret Minimization in Offline Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2306.01237 |