├── README.md ├── deep_rl_bootcamp.png └── deep_rl_survey.png /README.md: -------------------------------------------------------------------------------- 1 | # Deep Reinforcement Learning 2 | 3 | ### Introduction to Reinforcement Learning with David Silver, DeepMind 4 | Watch the lectures from DeepMind research lead David Silver's course on reinforcement learning, taught at University College London. 5 | 6 | [[Video lectures]](https://www.youtube.com/playlist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ) 7 | 8 | - Lecture 1: Introduction to Reinforcement Learning 9 | - Lecture 2: Markov Decision Processes 10 | - Lecture 3: Planning by Dynamic Programming 11 | - Lecture 4: Model-Free Prediction 12 | - Lecture 5: Model-Free Control 13 | - Lecture 6: Value Function Approximation 14 | - Lecture 7: Policy Gradient Methods 15 | - Lecture 8: Integrating Learning and Planning 16 | - Lecture 9: Exploration and Exploitation 17 | - Lecture 10: Case Study: RL in Classic Games 18 | 19 | ### Deep Reinforcement Learning: A Brief Survey 20 | Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath 21 | 22 | - [[Paper]](https://arxiv.org/abs/1708.05866) 23 | - [IEEE Signal Processing Magazine | November 2017](https://ieeexplore.ieee.org/document/8103164) 24 | 25 | [

](https://arxiv.org/abs/1708.05866) 26 | 27 | 28 | ### Spinning Up in Deep RL 29 | Educational resource produced by OpenAI that makes it easier to learn about deep reinforcement learning (deep RL). It includes the following resources: 30 | 31 | * a short [introduction](https://spinningup.openai.com/en/latest/spinningup/rl_intro.html) to RL terminology, kinds of algorithms, and basic theory, 32 | * an [essay](https://spinningup.openai.com/en/latest/spinningup/spinningup.html) about how to grow into an RL research role, 33 | * a [curated list](https://spinningup.openai.com/en/latest/spinningup/keypapers.html) of important papers organized by topic, 34 | * a well-documented [code repo](https://github.com/openai/spinningup) of short, standalone implementations of key algorithms, 35 | * and a few [exercises](https://spinningup.openai.com/en/latest/spinningup/exercises.html) to serve as warm-ups. 36 | 37 | [[Webpage]](https://spinningup.openai.com) 38 | 39 | ### Stanford CS234: Reinforcement Learning 40 | 41 | Lecture Series. Stanford CS234: Reinforcement Learning (Winter 2019) - with Prof. Emma Brunskill 42 | 43 | [[YouTube]](https://www.youtube.com/watch?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u&v=FgzM3zpZ55o) 44 | 45 | ### An Introduction to Deep Reinforcement Learning (2018) 46 | Vincent Francois-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare, Joelle Pineau 47 | 48 | [[PDF Book manuscript, Nov 2018]](https://arxiv.org/abs/1811.12560) 49 | 50 | ### CS294-112 Deep Reinforcement Learning 51 | 52 | Lecture Series. UC Berkeley. Fall 2018. 53 | 54 | Instructor : Sergey Levine 55 | 56 | [Webpage](http://rail.eecs.berkeley.edu/deeprlcourse/) 57 | [Youtube](https://www.youtube.com/playlist?list=PLkFD6_40KJIxJMR-j5A1mkxK26gh_qg37) 58 | 59 | 60 | ### CS885 Reinforcement Learning 61 | Lecture Series. University of Waterloo. Spring 2018 62 | 63 | Instructor: Pascal Poupart 64 | 65 | [Webpage](https://cs.uwaterloo.ca/~ppoupart/teaching/cs885-spring18/) 66 | [Youtube](https://www.youtube.com/playlist?list=PLdAoL1zKcqTXFJniO3Tqqn6xMBBL07EDc) 67 | 68 | ### Advanced Deep Learning & Reinforcement Learning 69 | 70 | Deepmind 2018. 71 | 72 | [Youtube](https://www.youtube.com/watch?v=iOh7QUZGyiU&list=PLqYmG7hTraZDNJre23vqCGIVpfZ_K2RZs) 73 | 74 | ### RLSS 2018 75 | Toronto 2018. 76 | 77 | [Videos](http://videolectures.net/DLRLsummerschool2018_toronto/) 78 | 79 | ### RLSS 2017 80 | Montreal 2017. 81 | 82 | [Videos](http://videolectures.net/deeplearning2017_montreal/) 83 | 84 | ### Deep RL Bootcamp 85 | Berkeley CA. Aug 2017 86 | 87 | [Slides & Videos](https://sites.google.com/view/deep-rl-bootcamp/lectures) 88 | 89 | ### Introduction to Reinforcement Learning 90 | DeepMind, 2015 91 | 92 | Instructor : David Silver 93 | 94 | [Youtube](https://www.youtube.com/watch?v=2pWv7GOvuf0&list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ) 95 | 96 | 97 | ### Deep RL Bootcamp, Berkeley (2017) 98 | By Pieter Abbeel, Chelsea Finn, Peter Chen, Andrej Karpathy et al. 99 | 100 | [[Webpage]](https://sites.google.com/view/deep-rl-bootcamp/lectures) 101 | 102 |

103 | 104 |

105 | 106 | ### Reinforcement Learning Book 107 | Written by [Richard Sutton](http://incompleteideas.net/index.html) and [Andrew Barto](http://www-anw.cs.umass.edu/~barto/). 108 | 109 | [[Webpage]](http://incompleteideas.net/book/the-book-2nd.html) [[PDF]](http://incompleteideas.net/book/RLbook2018.pdf) [[Goodreads]](https://www.goodreads.com/book/show/39813875-reinforcement-learning) 110 | 111 | ### Denny Britz: Reinforcement Learning 112 | Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course. All code is written in Python 3 and uses RL environments from OpenAI Gym. Advanced techniques use Tensorflow for neural network implementations. 113 | 114 | [[GitHub]](https://github.com/dennybritz/reinforcement-learning) 115 | -------------------------------------------------------------------------------- /deep_rl_bootcamp.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Deep_Reinforcement_Learning/fdf30e54fa9d55598525b8f811e2521b0dc6d771/deep_rl_bootcamp.png -------------------------------------------------------------------------------- /deep_rl_survey.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Machine-Learning-Tokyo/Deep_Reinforcement_Learning/fdf30e54fa9d55598525b8f811e2521b0dc6d771/deep_rl_survey.png --------------------------------------------------------------------------------