Deep Reinforcement Learning

最新推荐文章于 2022-10-21 09:12:47 发布
最新推荐文章于 2022-10-21 09:12:47 发布
阅读量157 收藏
点赞数
文章标签： 人工智能 数据结构与算法

Reinforcement-Learning-Introduction-Adaptive-Computation

http://incompleteideas.net/book/bookdraft2017nov5.pdf

http://incompleteideas.net/book/ebook/the-book.html

https://www.amazon.com/Reinforcement-Learning-Introduction-Adaptive-Computation/dp/0262193981

https://orbi.ulg.ac.be/bitstream/2268/27963/1/book-FA-RL-DP.pdf

http://videolectures.net/deeplearning2017_montreal/

http://www.clipconverter.cc/

 

Reinforcement Learning--David Silver

http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html

https://www.youtube.com/watch?v=2pWv7GOvuf0

 

COMBINING POLICY GRADIENT AND Q-LEARNING

https://arxiv.org/pdf/1611.01626.pdf

 

https://www.quora.com/Whats-the-difference-between-reinforcement-Learning-and-Deep-learning

https://stats.stackexchange.com/questions/144154/supervised-learning-unsupervised-learning-and-reinforcement-learning-workflow

https://www.quora.com/What-is-the-difference-between-supervised-unsupervised-reinforcement-and-deep-learning

https://www.quora.com/Is-reinforcement-learning-the-combination-of-unsupervised-learning-and-supervised-learning

https://www.quora.com/What-is-the-difference-between-supervised-unsupervised-reinforcement-and-deep-learning

 

https://www.oreilly.com/ideas/reinforcement-learning-for-complex-goals-using-tensorflow

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-6-partial-observability-and-deep-recurrent-q-68463e9aeefc

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0

 

最前沿：深度学习训练方法大革新，反向传播训练不再唯一

https://zhuanlan.zhihu.com/p/22143664

 

最前沿：让计算机学会学习Let Computers Learn to Learn

https://zhuanlan.zhihu.com/p/21362413?refer=intelligentunit

 

深度增强学习之Policy Gradient方法1

https://zhuanlan.zhihu.com/p/21725498

 

https://deepmind.com/blog/#decoupled-neural-interfaces-using-synthetic-gradients

 

ore from my Simple Reinforcement Learning with Tensorflow series:

  1. Part 0 — Q-Learning Agents
  2. Part 1 — Two-Armed Bandit
  3. Part 1.5 — Contextual Bandits
  4. Part 2 — Policy-Based Agents
  5. Part 3 — Model-Based RL
  6. Part 4 — Deep Q-Networks and Beyond
  7. Part 5 — Visualizing an Agent’s Thoughts and Actions
  8. Part 6 — Partial Observability and Deep Recurrent Q-Networks
  9. Part 7 — Action-Selection Strategies for Exploration
  10. Part 8 — Asynchronous Actor-Critic Agents (A3C)

https://keon.io/deep-q-learning/

Human-level control through deep reinforcement learning

https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf

 

http://rll.berkeley.edu/deeprlcourse/

https://bcourses.berkeley.edu/courses/1453965/pages/cs294-129-designing-visualizing-and-understanding-deep-neural-networks

 

https://cs.stanford.edu/people/karpathy/convnetjs/demo/rldemo.html

 

如何用简单例子讲解 Q - learning 的具体过程？

https://www.zhihu.com/question/26408259

 

https://deeplearning4j.org/reinforcementlearning.html

https://deeplearning4j.org/neuralnet-overview.html

https://devblogs.nvidia.com/parallelforall/deep-learning-nutshell-reinforcement-learning/

https://medium.com/beyond-intelligence/reinforcement-learning-or-evolutionary-strategies-nature-has-a-solution-both-8bc80db539b3

https://medium.com/ai-society/my-first-experience-with-deep-reinforcement-learning-1743594f0361

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0

http://neuro.cs.ut.ee/demystifying-deep-reinforcement-learning/

 

 

More from my Simple Reinforcement Learning with Tensorflow series:

  1. Part 0 — Q-Learning Agents
  2. Part 1 — Two-Armed Bandit
  3. Part 1.5 — Contextual Bandits
  4. Part 2 — Policy-Based Agents
  5. Part 3 — Model-Based RL
  6. Part 4 — Deep Q-Networks and Beyond
  7. Part 5 — Visualizing an Agent’s Thoughts and Actions
  8. Part 6 — Partial Observability and Deep Recurrent Q-Networks
  9. Part 7 — Action-Selection Strategies for Exploration
  10. Part 8 — Asynchronous Actor-Critic Agents (A3C)

Deep Reinforcement Learning 深度增强学习资源 (持续更新）

https://zhuanlan.zhihu.com/p/20885568

深度解读AlphaGo

https://zhuanlan.zhihu.com/p/20893777

深度学习论文阅读路线图 Deep Learning Papers Reading Roadmap

https://zhuanlan.zhihu.com/p/23080129

ICLR 2017 DRL相关论文

https://zhuanlan.zhihu.com/p/23807875

 

https://www.intelnervana.com/demystifying-deep-reinforcement-learning/

http://www.jmlr.org/papers/volume6/murphy05a/murphy05a.pdf 

https://deepmind.com/research/publications/

https://deepmind.com/blog/alphago-zero-learning-scratch/

Mastering the Game of Go without Human Knowledge

https://www.nature.com/articles/doi:10.1038/nature24270

https://en.wikipedia.org/wiki/State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action

DQN 从入门到放弃1 DQN与增强学习

https://zhuanlan.zhihu.com/p/21262246?refer=intelligentunit

DQN 从入门到放弃4 动态规划与Q-Learning

https://zhuanlan.zhihu.com/p/21378532?refer=intelligentunit

DQN从入门到放弃5 深度解读DQN算法

https://zhuanlan.zhihu.com/p/21421729

 

强化学习系列之九:Deep Q Network (DQN)

http://www.algorithmdog.com/drl

weixin_34334744
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Relational Deep Reinforcement Learning
半夏微凉的博客
04-25 943
Abstract 我们介绍了一种深度强化学习的方法，它通过结构化感知和关系推理提高了传统方法的效率、泛化能力和可解释性。它使用self-attention来迭代推理场景中实体之间的关系，并指导无模型策略。我们的结果表明，在一种名为Box-World的新的导航和规划任务中，我们的agent找到了可解释的解决方案，这些解决方案在样本复杂性、泛化到比训练期间所经历的更复杂的场景的能力以及整体性能方面都有...
Deep reinforcement learning with relational inductive biases 笔记
想写就写咯
02-22 675
文章目录前言背景MethodRL方法输入模块关系模块输出模块实验BOX-WORLD 前言 这是一个使用结构化特征上关系推理的机制帮助model-free的深度强化学习的方法，提高了表现、学习有效性、泛化性、可解释性。这篇文章的主要贡献就是介绍一种技术，通过关系归纳偏置来表征和推理深度强化学习中agent的状态。 背景 深度强化学习在一些具有挑战性的问题上实现非凡的效果很大程度上是因为其在如何学习和...
DeepMind 关系型深度强化学习 Relational Deep Reinforcement Learning
04-03
Relational Deep Reinforcement Learning--We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning. It uses self-attention to iteratively reason about the relations between entities in a scene and to guide a model-free policy. Our results show that in a novel navigation and planning task called Box-World, our agent finds interpretable solutions that improve upon baselines in terms of sample complexity, ability to generalize to more complex scenes than experienced during training, and overall performance. In the StarCraft II Learning Environment, our agent achieves state-of-the-art performance on six mini-games – surpassing human grandmaster performance on four. By considering architectural inductive biases, our work opens new directions for overcoming important, but stubborn, challenges in deep RL.
Relational Deep Reinforcement Learning（DeepMind提出关系性深度强化学习：在星际争霸2任务中获得最优水平）
06-08
2018.6.8，DeepMind提出关系性深度强化学习：在星际争霸2任务中获得最优水平，在本文中，我们介绍了一种深度强化学习方法，它可以通过结构化感知和关系推理提高常规方法的效率、泛化能力和可解释性。
Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-net
08-01
The topic of this book is Reinforcement Learning—which is a subfield of Machine Learning—focusing on the general and challenging problem of learning optimal behavior in complex environment. The learning process is driven only by reward value and observations obtained from the environment. This model is very general and can be applied to many practical situations from playing games to optimizing complex manufacture processes. Due to flexibility and generality, the field of Reinforcement Learning is developing very quickly and attracts lots of attention both from researchers trying to improve existing or create new methods, as well as from practitioners interested in solving their problems in the most efficient way. This book was written as an attempt to fill the obvious lack of practical and structured information about Reinforcement Learning methods and approaches. On one hand, there are lots of research activity all around the world, new research papers are being published almost every day, and a large portion of Deep Learning conferences such as NIPS or ICLR is dedicated to RL methods. There are several large research groups focusing on RL methods application in Robotics, Medicine, multi-agent systems, and others. The information about the recent research is widely available, but is too specialized and abstract to be understandable without serious efforts. Even worse is the situation with the practical aspect of RL application, as it is not always obvious how to make a step from the abstract method described in the mathematical-heavy form in a research paper to a working implementation solving actual problem. This makes it hard for somebody interested in the field to get an intuitive understanding of methods and ideas behind papers and conference talks. There are some very good blog posts about various RL aspects illustrated with working examples,
deep reinforcement learning
10-25
深度增强学习（Deep Reinforcement Learning，简称DeepRL）是人工智能领域的一个重要分支，它结合了深度学习（Deep Learning，简称DL）与增强学习（Reinforcement Learning，简称RL）的技术，用于处理复杂决策过程中...
An Introduction to Deep Reinforcement Learning.pdf
08-26
而Fitted Q-learning和Deep Q-Networks（DQN）则引入了近似函数，尤其是神经网络，来处理大规模状态空间。DQN的一些改进版本，如Double DQN和Dueling Network架构，旨在解决过估计问题和分离状态价值和优势功能。...
Deep Reinforcement Learning Hands-On Apply modern RL methods,
02-22
This practical guide will teach you how deep learning (DL) can be used to solve complex real-world problems. Key Features Explore deep reinforcement learning (RL), from the first principles to the latest algorithms Evaluate high-profile RL methods, includ。
Tutorial: Deep Reinforcement Learning
08-14
David Silver, Google DeepMind，深度强化学习的教程ppt
Deep Reinforcement Learning Hands-On
10-05
Deep Reinforcement Learning Hands-On Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more by Maxim Lapan Publisher: Packt Publishing Release Date: June 2018 ISBN: 9781788834247
deep reinforcement learning for nlp
09-28
使用强化学习的技术处理自然语言处理的相关问题。deep reinforcement learning for nlp on ACL 2018
中文翻译《Human-level control through deep reinforcement》
01-11
对论文《Human-level control through deep reinforcement》的中文翻译的文档
Deep Reinforcement Learning for Dialogue Generation
ryanloucc的博客
11-22 1624
关键词reinforcement learing，seq2seq来源EMNLP 2016.06.05问题目前的 seq2seq 模型做对话生成存在两个问题： 当前的 seq2seq 模型是这么去训练的，在给定对话上下文后，用最大似然估计作为目标函数，预测下一轮对话。但是 MLE 训练出来的模型并不能够产生有趣、多样、有信息量的反馈。 另一方面基于 MLE 的 seq2seq 模型不能够排除重复回复，
2022年最值得阅读的强化学习书籍
最新发布
weixin_42188287的博客
10-21 3646
推荐了九本强化学习领域最新的比较权威的书籍，从初学者到进阶都可以使用。
Deep Reinforcement Learning - 1. DDPG原理和算法
热门推荐
kenneth_yu的博客
11-08 14万+
Deep Reinforcement Learning - 1. DDPG原理和算法 背景描述 DDPG的定义和应用场景 DDPG算法相关基本概念定义 DDPG实现框架和算法 DDPG对于DPG的关键改进 下一篇 以下用RL作为Reinforcement Learning 的简称。背景描述概括来说，RL要解决的问
Deep Reinforcement Learning 基础知识（DQN方面）
Flood Sung的专栏
01-25 9万+
## Introduction 深度增强学习Deep Reinforcement Learning是将深度学习与增强学习结合起来从而实现从Perception感知到Action动作的端对端学习的一种全新的算法。简单的说，就是和人类一样，输入感知信息比如视觉，然后通过深度神经网络，直接输出动作，中间没有hand-crafted工作。深度增强学习具备使机器人实现完全自主的学习一种甚至多种技能的潜力。
对Attention is all you need 的理解
mijiaoxiaosan的博客
06-14 6万+
对谷歌Attention is all you need 的理解。
深度强化学习精要：Grokking Deep Reinforcement Learning
"Manning.Grokking.Deep.Reinforcement.Learning.2020.10.pdf - 一本关于深度强化学习的专业书籍，由Miguel Morales撰写，Charles Isbell, Jr.作序，由Manning出版社出版。内容涵盖深度强化学习的理论与实践，旨在...
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值