https://zhuanlan.zhihu.com/p/20885568
Deep Reinforcement Learning深度增強學習可以說發源於2013年DeepMind的Playing Atari with Deep Reinforcement Learning 一文,之後2015年DeepMind 在Nature上發表了Human Level Control through Deep Reinforcement Learning一文使Deep Reinforcement Learning得到了較廣泛的關注,在2015年涌現了較多的Deep Reinforcement Learning的成果。而2016年,隨着AlphaGo的出現,Deep Reinforcement Learning 將進入全面發展的階段。
Deep Reinforcement Learning面向決策與控制問題,而決策與控制很大程度上決定了人工智能的發展水平。也因此,AlphaGo的出現具有里程碑的意義。Deep Reinforcement Learning研究使用深度神經網絡來解決決策控制問題,是深度學習領域最前沿的研究方向之一。
本文主要收集與Deep Reinforcement Learning相關的各種資料,希望對有興趣研究的童鞋有所幫助。接下來,本專欄將由我繼續發佈Deep Reinforcement Learning的相關文章。
PS:最新的資料會在資料前方標出。
1 學習資料
1)增強學習相關課程:
- David Silver的增強學習課程(有視頻和ppt): http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html
- 最好的增強學習教材:Sutton & Barto Book: Reinforcement Learning: An Introduction
- Nando de Freitas的深度學習課程 (有視頻有ppt有作業):Machine Learning
- Michael Littman的增強學習課程:https://www.udacity.com/course/reinforcement-learning–ud600
- Pieter Abbeel 的AI課程(包含增強學習,使用Pacman實驗):Artificial Intelligence
- Pieter Abbeel 的深度增強學習課程:CS 294 Deep Reinforcement Learning, Fall 2015
- Pieter Abbeel 的 高級機器人技術(Advanced Robotics): CS287 Fall 2015
- 最新機器人專題課程Penn(2016年開課):Specialization
- (最新)Deep Learning Summer School:pptsvideos
2)深度學習相關課程:
- Fei Fei Li的用於視覺識別的卷積神經網絡 : CS231n Convolutional Neural Networks for Visual Recognition
- Andrew Ng(一個是Coursera上的課程,一個是Stanford的課程):Machine LearningCS 229: Machine Learning
- Hinton的神經網絡課程(Neural Network for Machine Learning)(2012年的)Coursera - Free Online Courses From Top Universities
3)深度增強學習相關blog:
- drl的入門博客(感謝知友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 深度增強學習相關講座
- 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:深度增強學習TutorialAlphaGo Tutorial
- Pieter Abbeel: https://www.youtube.com/watch?v=evq4p1zhS7Q
- Sergey Levine: Deep Robotic Learning
- John Schulman:Machine Learning Summer School
3 論文資料
- 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
這兩個人收集的基本涵蓋了當前deep reinforcement learning 的論文資料。目前確實不多。
4 大牛與企業情況:
- DeepMind:http://www.deepmind.com/publications.html
- OpenAI: OpenAI Gym
- Pieter Abbeel 團隊(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 進展:Lerrel PintoRuslan Salakhutdinov
- Prefered Networks: (日本創業公司)Preferred Networks
- Osaro:www.osaro.com
5 會議情況
6 開源代碼
在github可以找到dqn,ddpg,a3c, trpo 等深度增強學習典型算法的代碼,以下爲一些舉例的開源代碼:
- 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