搜索结果: 1-5 共查到“理学 Bandits”相关记录5条 . 查询时间(0.107 秒)
Linear Bandits in High Dimension and Recommendation Systems
Services automation browsing space
2015/8/21
A large number of online services provide automated recommendations to help users to navigate through a large collection of items. New items (products, videos, songs, advertisements) are suggested on ...
Bandits with heavy tail
Bandits heavy tail
2012/11/22
The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributi...
Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret
Uncontrolled Restless Bandits Logarithmic Regret Optimization and Control
2011/9/15
Abstract: In this paper we consider the problem of learning the optimal policy for the uncontrolled restless bandit problem. In this problem only the state of the selected arm can be observed, the sta...
Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards
Network Optimization Unknown Variables
2010/11/24
In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of interest is regret, de...
PAC-Bayesian aggregation and multi-armed bandits
PAC-Bayesian aggregation multi-armed bandits
2010/11/22
This habilitation thesis presents several contributions to (1) the PAC-Bayesian analysis of statistical learning, (2) the three aggregation problems: given d functions, how to predict as well as (i) ...