专栏名称: 机器学习研究会
机器学习研究会是北京大学大数据与机器学习创新中心旗下的学生组织,旨在构建一个机器学习从事者交流的平台。除了及时分享领域资讯外,协会还会举办各种业界巨头/学术神牛讲座、学术大牛沙龙分享会、real data 创新竞赛等活动。
目录
相关文章推荐
量子位  ·  全网都在扒的DeepSeek团队,是清北应届 ... ·  18 小时前  
爱可可-爱生活  ·  “从想法到手办,只要10分钟” ... ·  昨天  
宝玉xp  ·  回复@Le_Ethan:对,不仅适用于 ... ·  昨天  
黄建同学  ·  有时间的可以学一下 Andrej ... ·  3 天前  
51好读  ›  专栏  ›  机器学习研究会

【推荐】深度增强学习概览

机器学习研究会  · 公众号  · AI  · 2017-01-27 22:45

正文


点击上方“机器学习研究会”可以订阅哦
摘要
 

转自:爱可可-爱生活

论文《Deep Reinforcement Learning: An Overview》摘要:

We give an overview of recent exciting achievements of deep reinforcement learning (RL). We start with background of deep learning and reinforcement learning, as well as introduction of testbeds. Next we discuss Deep Q-Network (DQN) and its extensions, asynchronous methods, policy optimization, reward, and planning. After that, we talk about attention and memory, unsupervised learning, and learning to learn. Then we discuss various applications of RL, including games, in particular, AlphaGo, robotics, spoken dialogue systems (a.k.a. chatbot), machine translation, text sequence prediction, neural architecture design, personalized web services, healthcare, finance, and music generation. We mention topics/papers not reviewed yet. After listing a collection of RL resources, we close with discussions.


链接:

https://arxiv.org/abs/1701.07274


原文链接:

http://weibo.com/1402400261/EsI5K3mNz?from=page_1005051402400261_profile&wvr=6&mod=weibotime&type=comment#_rnd1485525843118

“完整内容”请点击【阅读原文】
↓↓↓