StanfordAdvanced
CS234: Reinforcement Learning
Stanford's graduate-level reinforcement learning course taught by Emma Brunskill.
Duration60+ hours
PriceFree
FormatVideo
LevelAdvanced
What you'll learn
- Markov decision processes and dynamic programming
- Model-free prediction and control algorithms
- Deep Q-learning, policy gradients, and actor-critic methods
- Imitation learning and batch reinforcement learning
About this course
A rigorous theoretical and applied treatment of reinforcement learning. Topics include Markov decision processes, model-free policy evaluation, Q-learning, policy search, imitation learning, and offline RL. Lecture notes and assignments are published on web.stanford.edu/class/cs234. We are not affiliated with Stanford University.
Prerequisites
Proficiency in Python, linear algebra, and machine learning fundamentals.