Skip to content
InfratoApp

Stanford University · Course

Deep Reinforcement Learning (CS224R)

Deep Reinforcement Learning (CS224R) on Stanford Online is a ten-week graduate course on algorithms that learn behaviour from experience using deep neural networks, with an applied, deep-learning focus and use cases in robotics and motor control.

Open at Stanford University ↗Common questions

Who it suits

  • Engineers with machine learning and PyTorch experience who want practical deep RL.
  • People interested in robotics and motor control applications of reinforcement learning.

What it covers

  • Methods for learning from demonstrations.
  • Both model-based and model-free deep RL methods.
  • Learning from offline datasets, and multi-task techniques such as goal-conditioned RL, meta-RL and unsupervised skill discovery.

Before you start

  • Stanford lists a conferred bachelor’s degree with an undergraduate GPA of 3.0 or better.
  • Machine learning at the level of CS229, and some familiarity with deep learning; assignments use PyTorch.
  • Some familiarity with reinforcement learning basics and Markov decision processes.

Common questions about Deep Reinforcement Learning (CS224R)

How long is it?
Stanford lists 10 weeks at 15 to 20 hours a week, for 3 academic units.
How does it differ from CS234?
Stanford says the two complement each other, and that this one has a more applied, deep learning focus with emphasis on robotics and motor control.
Is it open for enrolment?
Stanford’s page said it was not open at the time of reading, and noted the course would next open in 2027-28. Check the page for current availability.

More like this

Keep learning on Infrato

Where this comes from

Written from Stanford University’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Stanford University and this is not an endorsement.