Resources to get started with deep reinforcement learning

Question

Assume the learner is proficient with artificial neural networks, and has some background in reinforcement learning. What are some good resources (books/videos/papers/GitHub repo/etc.) to get started with deep reinforcement learning?

Answer 1

A nice introduction deep reinforcement learning by Lex Fridman (2019-01): https://youtu.be/zR11FLZ-O9M

2 complimentary, easy-to-read blog posts to get started on deep reinforcement learning: the first one focuses on policy gradients, the second one focuses on deep Q-learning.

1. Deep Reinforcement Learning: Pong from Pixels (mirror) by Andrej Karpathy (May 31, 2016).
2. Demystifying Deep Reinforcement Learning (mirror) by Tambet Matiise on Nervana (December 21, 2015)

Then, two more in-depth resources:

1. 10 videos, ~90 minutes each: Advanced Topics 2015 (COMPM050/COMPGI13) (mirror) on Reinforcement Learning by David Silver (2015)
2. 455-page free book: Reinforcement Learning: An Introduction (2nd Edition) by Richard S. Sutton and Andrew G. Barto (2016)

To start coding:

1. Learning Reinforcement Learning (with Code, Exercises and Solutions) (mirror) by Denny Britz (October 2, 2016)
2. Minimal and Clean Reinforcement Learning Examples (2017)
3. Using Keras and Deep Q-Network to Play FlappyBird (mirror, code) by Ben Lau (July 10, 2016) (the code is straightforward to run on Ubuntu)
4. Using Keras and Deep Deterministic Policy Gradient to play TORCS (mirror, code) by Ben Lau (October 11, 2016) (note: installing the gym_torcs requirement to have the code run may take some time, and instructions are only given for Linux).

More links:

• A curated list of resources dedicated to reinforcement learning.

Answer 2

You can see many resources on github already including this recent list of Deep RL papers

Also checkout some implementations such as Deep Q learning

And here is a nice video by David Silver at RLDM videolectures.net deep RL