码迷,mamicode.com
首页 > 其他好文 > 详细

Introducing Deep Reinforcement

时间:2018-11-16 13:26:49      阅读:239      评论:0      收藏:0      [点我收藏+]

标签:schedule   bre   nsf   anon   potential   aging   access   tail   ack   

 

The manuscript of Deep Reinforcement Learning is available now! It makes significant improvements to Deep Reinforcement Learning: An Overview, which has received 100+ citations, by extending its latest version more than one year ago from 70 pages to 150 pages.

It draws a big picture of deep reinforcement learning (RL) with many details. It covers contemporary work in historical contexts. It endeavours to answer the following questions: 1) Why deep? 2) What is the state of the art? and, 3) What are the issues, and potential solutions? It attempts to help those who want to get more familiar with deep RL, and to serve as a reference for people interested in this fascinating area, like professors, researchers, students, engineers, managers, investors, etc. Shortcomings and mistakes are inevitable; comments and criticisms are welcome.

The manuscript introduces AI, machine learning, and deep learning briefly, and provides a mini tutorial for reinforcement learning. The following figure illustrates relationships among these concepts, with major contents for machine learning and AI .Deep reinforcement learning is reinforcement learning integrated with deep learning, or deep artificial neural networks. A blog is dedicated to Resources for Deep Reinforcement Learning.

 
技术分享图片

The manuscript covers six core elements: value function, policy, reward, model, exploration vs. exploitation, and representation; six important mechanisms: attention and memory, unsupervised learning, hierarchical RL, multi-agent RL, relational RL, and learning to learn; and twelve applications: games, robotics, natural language processing (NLP), computer vision, finance, business management, healthcare, education, energy, transportation, computer systems, and, science, engineering, and art.

 
技术分享图片

Deep reinforcement learning has made exceptional achievements, e.g., DQN applying to Atari games ignited this wave of deep RL, and AlphaGo (Zero) and DeepStack set landmarks for AI. Deep RL has many newly invented algorithms/architectures, e.g., DQNA3CTRPOPPODDPGTrust-PCLGPSUNREALDNC, etc. Moreover, deep RL has been enjoying very abound and diverse applications, e.g., Capture the FlagDota 2StarCraft IIroboticscharacter animationconversational AIneural architecture design (AutoML)data center coolingrecommender systemsdata augmentationmodel compressioncombinatorial optimizationprogram synthesistheorem provingmedical imagingmusic, and chemical retrosynthesis, so on and so forth. A blog is dedicated to Reinforcement Learning applications.

In general, RL is probably helpful, if a problem can be regarded as or transformed to a sequential decision making problem, and states, actions, maybe rewards, can be constructed; sometimes the problem may not appear as an RL problem on the surface. Roughly speaking, if a task involves some manual designed “strategy”, then there is a chance for reinforcement learning to help. Creativity would push the frontiers of deep RL further with respect to core elements, important mechanisms, and applications.

Albeit being so successful, deep RL encounters many issues, like credit assignment, sparse reward, sample efficiency, instability, divergence, interpretability, safety, etc.; even reproducibility is an issue.

 
技术分享图片

Six research directions are proposed as both challenges and opporrtunities. There are already some progress in these directions, e.g., DopamineTStarBotsMORELGQN, visual reasoningneural-symbolic learningUPNcausal InfoGANmeta-gradient RL, along with many applications as above.

  1. systematic, comparative study of deep RL algorithms
  2. “solve” multi-agent problems
  3. learn from entities, but not just raw inputs
  4. design an optimal representation for RL
  5. AutoRL
  6. develop killer applications for (deep) RL

It is desirable to integrate RL more deeply with AI, with more intelligence in the end-to-end mapping from raw inputs to decisions, to incorporate knowledge, to have common sense, to be more efficient, to be more interpretable, and to avoid obvious mistakes, etc., rather than working as a blackbox.

 
技术分享图片

Deep learning and reinforcement learning, being selected as one of the MIT Technology Review 10 Breakthrough Technologies in 2013 and 2017 respectively, will play their crucial roles in achieving artificial general intelligence. David Silver proposed a conjecture: artificial intelligence = reinforcement learning + deep learning (AI = RL + DL). We will see both deep learning and reinforcement learning prospering in the coming years and beyond. Deep learning is exploding. It is the right time to nurture, educate and lead the market for reinforcement learning.

Deep learning, in this third wave of AI, will have deeper influences, as we have already seen from its many achievements. Reinforcement learning, as a more general learning and decision making paradigm, will deeply influence deep learning, machine learning, and artificial intelligence in general.

Introducing Deep Reinforcement

标签:schedule   bre   nsf   anon   potential   aging   access   tail   ack   

原文地址:https://www.cnblogs.com/alan-blog-TsingHua/p/9968595.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!