Lecture series
Reinforcement Learning - David Silver / UCL & DeepMind
The canonical free RL lecture series by David Silver - lead researcher behind AlphaGo and AlphaZero. Covers MDPs dynamic programming Q-learning policy gradients and more.
Ratings
Course details
Difficulty
Intermediate (some subject knowledge needed)
Length
10 – 40 hrs
Prerequisites
Light
Updated
2015
Exercises
No
Certificate
No