Utility-based Dueling Bandits as a Partial Monitoring Game
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2015
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914848845070336 |
|---|---|
| author | Gajane, Pratik Urvoy, Tanguy |
| author_facet | Gajane, Pratik Urvoy, Tanguy |
| contents | Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with expect advice, dynamic pricing, dark pools, and label efficient prediction. We study the utility-based dueling bandit problem as an instance of partial monitoring problem and prove that it fits the time-regret partial monitoring hierarchy as an easy - i.e. Theta (sqrt{T})- instance. We survey some partial monitoring algorithms and see how they could be used to solve dueling bandits efficiently. Keywords: Online learning, Dueling Bandits, Partial Monitoring, Partial Feedback, Multiarmed Bandits |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1507_02750 |
| institution | arXiv |
| publishDate | 2015 |
| record_format | arxiv |
| spellingShingle | Utility-based Dueling Bandits as a Partial Monitoring Game Gajane, Pratik Urvoy, Tanguy Machine Learning Partial monitoring is a generic framework for sequential decision-making with incomplete feedback. It encompasses a wide class of problems such as dueling bandits, learning with expect advice, dynamic pricing, dark pools, and label efficient prediction. We study the utility-based dueling bandit problem as an instance of partial monitoring problem and prove that it fits the time-regret partial monitoring hierarchy as an easy - i.e. Theta (sqrt{T})- instance. We survey some partial monitoring algorithms and see how they could be used to solve dueling bandits efficiently. Keywords: Online learning, Dueling Bandits, Partial Monitoring, Partial Feedback, Multiarmed Bandits |
| title | Utility-based Dueling Bandits as a Partial Monitoring Game |
| topic | Machine Learning |
| url | https://arxiv.org/abs/1507.02750 |