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?
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.
- Deep Reinforcement Learning: Pong from Pixels (mirror) by Andrej Karpathy (May 31, 2016).
- Demystifying Deep Reinforcement Learning (mirror) by Tambet Matiise on Nervana (December 21, 2015)
Then, two more in-depth resources:
- 10 videos, ~90 minutes each: Advanced Topics 2015 (COMPM050/COMPGI13) (mirror) on Reinforcement Learning by David Silver (2015)
- 455-page free book: Reinforcement Learning: An Introduction (2nd Edition) by Richard S. Sutton and Andrew G. Barto (2016)
To start coding:
- Learning Reinforcement Learning (with Code, Exercises and Solutions) (mirror) by Denny Britz (October 2, 2016)
- Minimal and Clean Reinforcement Learning Examples (2017)
- 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)
- Using Keras and Deep Deterministic Policy Gradient to play TORCS (mirror, code) by Ben Lau (October 11, 2016) (note: installing the
gym_torcsrequirement to have the code run may take some time, and instructions are only given for Linux).