zoukankan      html  css  js  c++  java
  • 英文论文常用句子

    ABSTRACT

    In this paper, we propose a novel Deep Reinforcement Learning framework for news recommendation . --------------



    Therefore, to address the aforementioned  
    challenges, we propose a Deep Q-Learning based recommendation   framework, which can model future reward explicitly. 

    1 INTRODUCTION

    Several groups of methods are proposed to solve the online personalized news recommendation problem, including content based methods...........


    Therefore, in this paper, we propose a Deep Reinforcement Learning framework that can help to address these three challenges in online personalized news recommendation. First, 


    Our contribution can be summarized as below:

    We propose a reinforcement learning framework to do online  Although we focus on  news recommendation, our framework can be generalized to many other recommendation problems.

    We consider user activeness to help improve recommendation accuracy, which can provide extra information than  simply using user click labels.

    A more effective exploration method Dueling Bandit Gradient Descent is applied, which avoids the recommendation accuracy drop induced by classical exploration methods, e.g.,ϵ-greedy and Upper Confdence Bound.



    Our system has been deployed online in a commercial news recommendation application. Extensive ofine and online experiments have shown the superior performance of our  methods.

    The rest of the paper is organized as follows. Related work is discussed in Section 2. Then, in Section 3 we present the problem defnitions. Our method is introduced in Section 4.

    After that, the experimental results are shown in Section 5. Finally, brief conclusions are given in Section 6. 





  • 相关阅读:
    阿里云CDN缓存加速学习总结
    阿里云SLB学习总结
    zabbix3.2安装
    drf中的增删改查接口
    drf中二次封装Response
    drf常用模块
    Django—auth模块
    csrf跨站请求伪造与CBV装饰器
    Django—cookie与session
    Django—中间件(待更新)
  • 原文地址:https://www.cnblogs.com/zle1992/p/10479533.html
Copyright © 2011-2022 走看看