GENALTI GIANMARCO | Cycle: XXXVIII |
Advisor: GATTI NICOLA
Tutor: CERI STEFANO
Major Research topic:
Multi-Armed Bandit Models in Realistic Settings: Theoretical Foundations and Algorithms
Abstract:
This work aims to explore several research directions in stochastic sequential decision-making. The stochastic multi-armed bandit is a theoretical framework in which an agent must repeatedly decide among a predefined set of possible actions while receiving sequential feedback. The main challenge is balancing exploiting the most promising actions with exploring the whole set. The classic model is restrictive when it comes to real-world applications: some of its core assumptions, such as the stationarity of the rewards, the good behavior of the noise, or the absence of constraints, severely limit the breadth of realistic applications for multi-armed bandits. This research investigates the theoretical foundations of such settings, where assumptions are relaxed or completely removed. Some algorithms are proposed to deal with these complex environments, and their theoretical guarantees are characterized.
Cookies
We serve cookies. If you think that's ok, just click "Accept all". You can also choose what kind of cookies you want by clicking "Settings".
Read our cookie policy
Cookies
Choose what kind of cookies to accept. Your choice will be saved for one year.
Read our cookie policy
-
Necessary
These cookies are not optional. They are needed for the website to function. -
Statistics
In order for us to improve the website's functionality and structure, based on how the website is used. -
Experience
In order for our website to perform as well as possible during your visit. If you refuse these cookies, some functionality will disappear from the website. -
Marketing
By sharing your interests and behavior as you visit our site, you increase the chance of seeing personalized content and offers.