The branch of AI behind game-playing systems, robotics, and RLHF. Includes the DeepMind lecture series that introduced a generation to RL and hands-on courses where you train your own agents.
Sorted cheapest first. Click a column header to re-sort. Advanced learners with ML and probability.
| Course | Level | Duration | Price | Certificate | |
|---|---|---|---|---|---|
Stanford University |
advanced | 10 weeks (one quarter) | Free | No | Visit |
UC Berkeley |
advanced | One semester (~25 lectures) | Free | No | Visit |
Hugging Face |
intermediate | 8 units plus bonus units, self-paced | Free | Yes | Visit |
UCL / Google DeepMind (David Silver) · UCL / Google DeepMind |
intermediate | 10 lectures, ~1.5 hours each | Free | No | Visit |
OpenAI · OpenAI Academy |
intermediate | Self-paced (docs, exercises, and code) | Free | No | Visit |
University of Alberta / Alberta Machine Intelligence Institute · Coursera |
intermediate | 2 months at 10 hrs/week (4 courses) | Free to audit Free to audit · $49/mo |
Yes | Visit |
Udacity |
advanced | ~83 hours (about 4 months part-time) | Paid $249/mo |
Yes | Visit |
No payment required. Several of these are complete university courses.
Emma Brunskill's course covers tabular RL, deep Q-learning, policy gradients, exploration, offline RL, and RLHF with public lecture slides and assignments. A strong theory-plus-practice sequel to David Silver's lectures.
Sergey Levine's graduate course goes deep on policy gradients, actor-critic, model-based RL, offline RL, exploration, and inverse RL with PyTorch homework. For learners aiming at RL research or robotics who want the most advanced free syllabus available.
Train agents from Q-learning to PPO and multi-agent setups in Colab, publish them to the Hub, and compete on leaderboards. Ideal for learners who want deep RL to be practical and fun from the first unit, with a free certificate at the end.
David Silver's classic lectures cover MDPs, dynamic programming, Monte Carlo and TD learning, function approximation, policy gradients, and planning, closely tracking the Sutton and Barto textbook. Still the standard first RL course for anyone serious about the field.
OpenAI's educational package pairs a concise introduction to RL theory with clean reference implementations of VPG, TRPO, PPO, DDPG, TD3, and SAC, plus a curated key-papers list and exercises. Use it to bridge the gap between lecture understanding and writing your own deep RL code.
Watch everything free; pay only if you want graded assignments and a credential.
Taught by Martha and Adam White with guest appearances from Rich Sutton, this specialization implements the algorithms of the Sutton and Barto textbook from bandits to a complete capstone agent. The most rigorous MOOC path through RL fundamentals.
Structured programs with instructors, cohorts, projects or formal credentials.
Build DQN, policy-gradient, and multi-agent agents in Unity ML-Agents environments across three reviewed projects. Choose it for structured, project-graded practice in deep RL with mentor feedback.
Supervised and unsupervised learning, model evaluation, and the math behind it.