Generative Adversarial User Model for Reinforcement Learning Based Recommendation System
Generative Adversarial User Model for Reinforcement Learning Based Recommendation System ICML 2019 摘要： 本文是推荐系统和强化学习结合起来的应用： 主要是2点： 1 我们开发了一个生成式的对抗学习(GAN)公式来模拟用户的行为动态，并恢复她的奖励功能。通过联合最小二乘优化算法，同时对这两个分量进
相关文章
- 1. Deep Learning Recommendation Model for Personalization and Recommendation Systems
- 2. AT-GAN: A Generative Attack Model for Adversarial Transferring on Generative Adversarial Nets
- 3. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 4. Model-Based Reinforcement Learning: Theory and Practice 译文
- 5. MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection 走读
- 6. [Reinforcement Learning] Model-Free Prediction
- 7. Reinforcement Learning（二）：Value-Based
- 8. [Reinforcement Learning] Model-Free Control
- 9. Reinforcement Learning（三）：Policy-Based
- 10. Reinforcement Learning强化学习系列之一：model-based learning
- 更多相关文章...
- • XSLT system-property() 函数 - XSLT 教程
- • Swift for 循环 - Swift 教程
- • Java Agent入门实战（三）-JVM Attach原理与使用
- • Flink 数据传输及反压详解
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Deep Learning Recommendation Model for Personalization and Recommendation Systems
- 2. AT-GAN: A Generative Attack Model for Adversarial Transferring on Generative Adversarial Nets
- 3. 论文笔记 Benchmarking Model-Based Reinforcement Learning
- 4. Model-Based Reinforcement Learning: Theory and Practice 译文
- 5. MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection 走读
- 6. [Reinforcement Learning] Model-Free Prediction
- 7. Reinforcement Learning（二）：Value-Based
- 8. [Reinforcement Learning] Model-Free Control
- 9. Reinforcement Learning（三）：Policy-Based
- 10. Reinforcement Learning强化学习系列之一：model-based learning