Reinforcement Learning Specialization
Self-paced
Yes
Python + probability
University of Alberta’s 4-course RL specialization — MDPs, Q-learning, policy gradients, real-world applications.
What you will learn:
- Markov decision processes
- Q-learning and SARSA
- Policy gradient methods
- Applications to robotics and games
Who it is for: ML engineers specializing in RL, robotics engineers, advanced researchers.
Honest take: Niche. Only take if you have a specific RL use case (robotics, agents, game AI).