I'm currently reading the 2nd edition of Reinforcement Learning: An Introduction and am watching the videos of David Silver's class on RL. I figured it would be a good idea to implement the algorithms and play a little bit with them. For the first chapter this turned out to be a lot of fun :)
- CS 294: Deep Reinforcement Learning (DRL): Advanced RL using deep learning methods
- Practical RL: From Yandex, contains some DRL content
- ShangtongZhang/reinforcement-learning-an-introduction: Code to generate all figures from Sutton & Barto's book
- dennybritz/reinforcement-learning: Many RL exercises
- awjuliani/DeepRL-Agents: Code for DRL
After getting familiar with the fundamentals, there are some interesting papers to read:
- Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." Nature 529.7587 (2016): 484-489.
- Barto, Andrew G., and Sridhar Mahadevan. "Recent advances in hierarchical reinforcement learning." Discrete Event Dynamic Systems 13.4 (2003): 341-379.
- Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." Nature 518.7540 (2015): 529-533.
- Diuk, Carlos, Andre Cohen, and Michael L. Littman. "An object-oriented representation for efficient reinforcement learning." Proceedings of the 25th international conference on Machine learning. ACM, 2008.
- Kober, Jens, J. Andrew Bagnell, and Jan Peters. "Reinforcement learning in robotics: A survey." The International Journal of Robotics Research 32.11 (2013): 1238-1274.