https://zhuanlan.zhihu.com/p/20885568
Deep Reinforcement Learning深度增强学习可以说发源于2013年DeepMind的Playing Atari with Deep Reinforcement Learning 一文,之后2015年DeepMind 在Nature上发表了Human Level Control through Deep Reinforcement Learning一文使Deep Reinforcement Learning得到了较广泛的关注,在2015年涌现了较多的Deep Reinforcement Learning的成果。而2016年,随着AlphaGo的出现,Deep Reinforcement Learning 将进入全面发展的阶段。
Deep Reinforcement Learning面向决策与控制问题,而决策与控制很大程度上决定了人工智能的发展水平。也因此,AlphaGo的出现具有里程碑的意义。Deep Reinforcement Learning研究使用深度神经网络来解决决策控制问题,是深度学习领域最前沿的研究方向之一。
本文主要收集与Deep Reinforcement Learning相关的各种资料,希望对有兴趣研究的童鞋有所帮助。接下来,本专栏将由我继续发布Deep Reinforcement Learning的相关文章。
PS:最新的资料会在资料前方标出。
1 学习资料
1)增强学习相关课程:
- David Silver的增强学习课程(有视频和ppt): http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html
- 最好的增强学习教材:Sutton & Barto Book: Reinforcement Learning: An Introduction
- Nando de Freitas的深度学习课程 (有视频有ppt有作业):Machine Learning
- Michael Littman的增强学习课程:https://www.udacity.com/course/reinforcement-learning–ud600
- Pieter Abbeel 的AI课程(包含增强学习,使用Pacman实验):Artificial Intelligence
- Pieter Abbeel 的深度增强学习课程:CS 294 Deep Reinforcement Learning, Fall 2015
- Pieter Abbeel 的 高级机器人技术(Advanced Robotics): CS287 Fall 2015
- 最新机器人专题课程Penn(2016年开课):Specialization
- (最新)Deep Learning Summer School:pptsvideos
2)深度学习相关课程:
- Fei Fei Li的用于视觉识别的卷积神经网络 : CS231n Convolutional Neural Networks for Visual Recognition
- Andrew Ng(一个是Coursera上的课程,一个是Stanford的课程):Machine LearningCS 229: Machine Learning
- Hinton的神经网络课程(Neural Network for Machine Learning)(2012年的)Coursera - Free Online Courses From Top Universities
3)深度增强学习相关blog:
- drl的入门博客(感谢知友Richard Huang)
1.Guest Post (Part I): Demystifying Deep Reinforcement Learning
2.Guest Post (Part II): Deep Reinforcement Learning with Neon
3.Blog Post (Part III): Deep Reinforcement Learning with OpenAI Gym
- Andrej Karpathy blog: Deep Reinforcement Learning: Pong from Pixels
2 深度增强学习相关讲座
- David Silver的:
ICLR 2015 part 1 https://www.youtube.com/watch?v=EX1CIVVkWdE
ICLR 2015 part 2 https://www.youtube.com/watch?v=zXa6UFLQCtg
UAI 2015 https://www.youtube.com/watch?v=qLaDWKd61Ig
RLDM 2015 Deep Reinforcement Learning
ICML 2016:深度增强学习TutorialAlphaGo Tutorial
- Pieter Abbeel: https://www.youtube.com/watch?v=evq4p1zhS7Q
- Sergey Levine: Deep Robotic Learning
- John Schulman:Machine Learning Summer School
3 论文资料
- GitHub - junhyukoh/deep-reinforcement-learning-papers: A list of recent papers regarding deep reinforcement learning
- GitHub - muupan/deep-reinforcement-learning-papers: A list of papers and resources dedicated to deep reinforcement learning
这两个人收集的基本涵盖了当前deep reinforcement learning 的论文资料。目前确实不多。
4 大牛与企业情况:
- DeepMind:http://www.deepmind.com/publications.html
- OpenAI: OpenAI Gym
- Pieter Abbeel 团队(已加入OpenAI):Pieter Abbeel---Associate Professor UC Berkeley---Co-Founder Gradescope---
- Satinder Singh:Home page for Satinder Singh (Baveja) and Reinforcement Learning
- CMU 进展:Lerrel PintoRuslan Salakhutdinov
- Prefered Networks: (日本创业公司)Preferred Networks
- Osaro:www.osaro.com
5 会议情况
6 开源代码
在github可以找到dqn,ddpg,a3c, trpo 等深度增强学习典型算法的代码,以下为一些举例的开源代码:
- GitHub - songrotek/DeepTerrainRL: terrain-adaptive locomotion skills using deep reinforcement learning
- GitHub - songrotek/async-rl: An attempt to reproduce the results of "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)
- GitHub - songrotek/rllab: rllab is a framework for developing and evaluating reinforcement learning algorithms.
- GitHub - songrotek/DRL-FlappyBird: Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)
- GitHub - songrotek/DeepMind-Atari-Deep-Q-Learner: The original code from the DeepMind article + my tweaks