bandit problem
d010396ca8abf6ead8cacc2c2f2f26c7-Paper.pdf
A multi-armed bandit (MAB) problem is one of the classic models of sequential decision making (Auer et al., 2002; Agrawal and Goyal, 2012, 2013a).
Technology:
Multi-ArmedBanditswithBoundedArm-Memory: Near-OptimalGuaranteesforBest-Arm IdentificationandRegretMinimization
In this setting, the arms arrive in a stream, and the number of arms that can be storedinthememory atanytime,isbounded.
Country:
- Europe > France > Île-de-France > Paris > Paris (0.05)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > Middle East > Jordan (0.04)
Technology:
Country:
- North America > Canada > Ontario > National Capital Region > Ottawa (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology:
Multi-Agent Learning with Heterogeneous Linear Contextual Bandits
UCB, wherein agents cooperatively minimize the group regret under the coordination of a central server.
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Europe > France > Auvergne-Rhône-Alpes > Isère > Grenoble (0.04)
Technology:
Country:
- North America > United States > California (0.14)
- North America > Canada > Alberta (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Context-lumpable stochastic bandits
Consider a recommendation platform that interacts with a finite set of users in an online fashion. Users arrive at the platform and receive a recommendation.
Country:
- North America > United States > California (0.14)
- North America > Canada > Alberta (0.14)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Country:
- North America > United States (0.04)
- Europe > France > Île-de-France > Paris > Paris (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology:
Technology:
- Information Technology > Artificial Intelligence > Machine Learning (1.00)
- Information Technology > Data Science > Data Mining > Big Data (0.48)
Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
Lijun Zhang is the corresponding author.
Country:
- Asia > China > Guangdong Province > Shenzhen (0.05)
- Asia > China > Hong Kong (0.04)
- Asia > China > Jiangsu Province > Nanjing (0.04)
- (4 more...)
Technology: