Basic Reinforcement Learning (RL)

This repository aims to provide an introduction series to reinforcement learning (RL) by delivering a walkthough on how to code different RL techniques.

Background review

A quick background review of RL is available here.

Tutorials:

• [x] Tutorial 1: Q-learning
• [x] Tutorial 2: SARSA
• [x] Tutorial 3: Exploring OpenAI gym
• [x] Tutorial 4: Q-learning in OpenAI gym
• [x] Tutorial 5: Deep Q-learning (DQN)
• [x] Tutorial 6: Deep Convolutional Q-learning
• [x] Tutorial 7: Reinforcement Learning with ROS and Gazebo
• [ ] Tutorial 8: Reinforcement Learning in DOOM (unfinished)
• [x] Tutorial 9: Deep Deterministic Policy Gradients (DDPG)
• [ ] Tutorial 10: Guided Policy Search (GPS) (unfinished)
• [ ] Tutorial 11: A review of different AI techniques for RL (WIP)
• [x] Tutorial 12: Reviewing Policy Gradient methods
• [ ] Tutorial 13: Continuous-state spaces with DQN (merged)
• [x] Tutorial 14: Benchmarking RL techniques
• [ ] Tutorial 15: Reviewing Vanilla Policy Gradient (VPG) (failed miserably)

References:

• Chris Watkins, Learning from Delayed Rewards, Cambridge, 1989 (thesis)
• Awesome Reinforcement Learning repository, aikorea/awesome-rl
• Reinforcement learning CS9417ML, School of Computer Science & Engineering, UNSW Sydney, http://www.cse.unsw.edu.au/~cs9417ml/RL1/index.html
• Reinforcement learning blog posts, https://studywolf.wordpress.com/2012/11/25/reinforcement-learning-q-learning-and-exploration/
• OpenAI gym docs, https://gym.openai.com/docs
• Vincent Bons implementations, https://gist.github.com/wingedsheep
• David Silver's Deep Reinforcement Learning talk, http://videolectures.net/rldm2015_silver_reinforcement_learning/
• Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., & Zaremba, W. (2016). OpenAI Gym. arXiv preprint arXiv:1606.01540.
• https://sites.google.com/view/deep-rl-bootcamp/lectures
• vmayoral/gym-cryptocurrencies