发帖
雷达卡
Top-k eXtreme Contextual Bandits with Arm Hierarchy
Rajat Sen 1 Alexander Rakhlin 2 3 Lexing Ying 4 3 Rahul Kidambi 3 Dean Foster 3 Daniel Hill 3
Inderjit S. Dhillon 5 3
Abstract 1. Introduction
The contextual bandit is a sequential decision-making
Motivated by modern applications, such as on- problem, in which, at every time step, the learner ob-
line advertisement and recommender systems, ...
京公网安备 11010802022788号
