Reinforcement learning course at Data Science Retreat
Switch branches/tags
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
assets
literature
notes
.gitignore
PITCHME.md
PITCHME.yaml
intro_to_tensorflow.ipynb
readme.md
resources.md
slides.pdf
supervised_learning.md
todo.md

readme.md

Materials for the reinforcement learning course at Data Science Retreat.

This course is aimed at students with a grasp of supervised learning - no prior understanding of reinforcement learning required.

The course materials are:

This repo also has machine learning and reinforcement learning literature. Further resources (video lectures, blog posts etc) are listed in dsr-rl/resources.md.

This project is built and maintained by Adam Green - adam.green@adgefficiency.com.

Content

  • background statistical concepts
  • Markov Decision processes
  • value function methods (DQN and it's extensions)
  • policy gradient methods
  • AlphaGo
  • practical advice for experiments
  • current state of the art

Goals for the course

Introduction to concepts, ideas and terminology. Familiarity with important literature. Understanding of the state of the field today. Practical strategies to run reinforcement learning experiments.

Where to go next

Further resources (video lectures, blog posts etc) are listed in dsr-rl/resources.md.