Reinforcement Learning Specialization

The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI).
Harnessing the full potential of artificial intelligence requires adaptive learning systems. Learn how Reinforcement Learning (RL) solutions help solve real-world problems through trial-and-error interaction by implementing a complete RL solution from beginning to end.
By the end of this Specialization, learners will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses or to apply AI tools and ideas to real-world problems. This content will focus on “small-scale” problems in order to understand the foundations of Reinforcement Learning, as taught by world-renowned experts at the University of Alberta, Faculty of Science.
The tools learned in this Specialization can be applied to game development (AI), customer interaction (how a website interacts with customers), smart assistants, recommender systems, supply chain, industrial control, finance, oil & gas pipelines, industrial control systems, and more.
WHAT YOU WILL LEARN

Build a Reinforcement Learning system for sequential decision making.
Understand the space of RL algorithms (Temporal- Difference learning, Monte Carlo, Sarsa, Q-learning, Policy Gradients, Dyna, and more).
Understand how to formalize your task as a Reinforcement Learning problem, and how to begin implementing a solution.
Understand how RL fits under the broader umbrella of machine learning, and how it complements deep learning, supervised and unsupervised learning

Coursera

University of Alberta,Alberta Machine Intelligence Institute

Fundamentals of Reinforcement Learning (Coursera)

Data Science

Dive into the world of Reinforcement Learning, a crucial subfield of Machine Learning that focuses on developing intelligent agents capable of making decisions based on interaction with their environment. This course provides an in-depth understanding of statistical learning techniques where an agent takes actions to maximize rewards. Ideal for those interested in interactive AI and automated decision-making processes.

Jun 22nd 2026

4 Weeks

ML Artificial Intelligence Machine Learning

Coursera

University of Alberta,Alberta Machine Intelligence Institute

A Complete Reinforcement Learning System (Capstone) (Coursera)

Data Science

In this final course of the Reinforcement Learning specialization, you will synthesize your acquired knowledge to build a complete reinforcement learning (RL) system. By tackling a real-world problem, you'll learn how each component—problem formulation, algorithm selection, parameter tuning, and representation design—works together in a cohesive solution. This capstone project requires you to create both the environment simulating your problem and an RL agent with neural network function approximation. You will also conduct a scientific study of your learning system, enhancing your ability to assess the robustness of RL agents.

Jun 22nd 2026

5-12 Weeks

Artificial Intelligence Algorithms Machine Learning

Coursera

University of Alberta,Alberta Machine Intelligence Institute

Sample-based Learning Methods (Coursera)

Data Science

Explore the world of sample-based learning methods in our comprehensive online course. Master intuitive yet effective algorithms like Monte Carlo methods and temporal difference learning techniques including Q-learning. Gain insights into combining model-based planning and TD updates for accelerated learning.

Jun 15th 2026

4 Weeks

Learning Artificial Intelligence Machine Learning

Coursera

University of Alberta,Alberta Machine Intelligence Institute

Prediction and Control with Function Approximation (Coursera)

Data Science

Discover how to tackle intricate problems with vast and potentially infinite state spaces by mastering prediction and control through function approximation. This course transforms the way you approach complex decision-making processes, teaching you to view value estimation as a supervised learning challenge. You'll develop agents capable of optimizing rewards by striking the perfect balance between generalizing well across states and discriminating effectively among them.

Jun 15th 2026

4 Weeks

Artificial Intelligence Machine Learning Prediction

Page 1