Reinforcement Learning is a subfield of Machine Learning, but is also a general purpose formalism for automated decision-making and AI. This course introduces you to statistical learning techniques where an agent explicitly takes actions and interacts with the world. Understanding the importance and challenges of learning agents that make decisions is of vital importance today, with more and more companies interested in interactive agents and intelligent decision-making.
Offered By
University of Alberta
Alberta Machine Intelligence Institute
Reinforcement Learning SpecializationUniversity of AlbertaAbout this Course
170,283 recent views
Learner Career Outcomes
25%
started a new career after completing these courses
11%
got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Course 1 of 4 in the
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.
Approx. 15 hours to complete
English
Subtitles: French, Portuguese (Brazilian), Russian, English, Spanish
What you will learn
Formalize problems as Markov Decision Processes
Understand basic exploration methods and the exploration / exploitation tradeoff
Understand value functions, as a general-purpose tool for optimal decision-making
Know how to implement dynamic programming as an efficient solution approach to an industrial control problem
Skills you will gain
Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems
Learner Career Outcomes
25%
started a new career after completing these courses
11%
got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Course 1 of 4 in the
Flexible deadlines
Reset deadlines in accordance to your schedule.
Intermediate Level
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.
Approx. 15 hours to complete
English
Subtitles: French, Portuguese (Brazilian), Russian, English, Spanish
Offered by
University of Alberta
UAlberta is considered among the world’s leading public research- and teaching-intensive universities. As one of Canada’s top universities, we’re known for excellence across the humanities, sciences, creative arts, business, engineering and health sciences.
Alberta Machine Intelligence Institute
The Alberta Machine Intelligence Institute (Amii) is home to some of the world’s top talent in machine intelligence. We’re an Alberta-based
Syllabus - What you will learn from this course
1 hour to complete
Welcome to the Course!
Welcome to: Fundamentals of Reinforcement Learning, the first course in a four-part specialization on Reinforcement Learning brought to you by the University of Alberta, Onlea, and Coursera. In this pre-course module, you'll be introduced to your instructors, get a flavour of what the course has in store for you, and be given an in-depth roadmap to help make your journey through this specialization as smooth as possible.
1 hour to complete
4 videos (Total 20 min), 2 readings
4 videos
Course Introduction5m
Meet your instructors!8m
Your Specialization Roadmap3m
2 readings
Reinforcement Learning Textbook10m
Read Me: Pre-requisites and Learning Objectives10m
4 hours to complete
An Introduction to Sequential Decision-Making
For the first week of this course, you will learn how to understand the exploration-exploitation trade-off in sequential decision-making, implement incremental algorithms for estimating action-values, and compare the strengths and weaknesses to different algorithms for exploration. For this week’s graded assessment, you will implement and test an epsilon-greedy agent.
4 hours to complete
8 videos (Total 46 min), 3 readings, 2 quizzes
8 videos
Learning Action Values4m
Estimating Action Values Incrementally5m
What is the trade-off?7m
Optimistic Initial Values6m
Upper-Confidence Bound (UCB) Action Selection5m
Jonathan Langford: Contextual Bandits for Real World Reinforcement Learning8m
Week 1 Summary3m
3 readings
Module 1 Learning Objectives10m
Weekly Reading30m
Chapter Summary30m
1 practice exercise
Sequential Decision-Making45m
3 hours to complete
Markov Decision Processes
When you’re presented with a problem in industry, the first and most important step is to translate that problem into a Markov Decision Process (MDP). The quality of your solution depends heavily on how well you do this translation. This week, you will learn the definition of MDPs, you will understand goal-directed behavior and how this can be obtained from maximizing scalar rewards, and you will also understand the difference between episodic and continuing tasks. For this week’s graded assessment, you will create three example tasks of your own that fit into the MDP framework.
3 hours to complete
7 videos (Total 36 min), 2 readings, 2 quizzes
7 videos
Examples of MDPs4m
The Goal of Reinforcement Learning3m
Michael Littman: The Reward Hypothesis12m
Continuing Tasks5m
Examples of Episodic and Continuing Tasks3m
Week 2 Summary1m
2 readings
Module 2 Learning Objectives10m
Weekly Reading30m
1 practice exercise
MDPs45m
3 hours to complete
Value Functions & Bellman Equations
Once the problem is formulated as an MDP, finding the optimal policy is more efficient when using value functions. This week, you will learn the definition of policies and value functions, as well as Bellman equations, which is the key technology that all of our algorithms will use.
3 hours to complete
9 videos (Total 56 min), 3 readings, 2 quizzes
9 videos
Value Functions6m
Rich Sutton and Andy Barto: A brief History of RL7m
Bellman Equation Derivation6m
Why Bellman Equations?5m
Optimal Policies7m
Optimal Value Functions5m
Using Optimal Value Functions to Get Optimal Policies8m
Week 3 Summary4m
3 readings
Module 3 Learning Objectives10m
Weekly Reading30m
Chapter Summary13m
2 practice exercises
[Practice] Value Functions and Bellman Equations45m
Value Functions and Bellman Equations45m
4 hours to complete
Dynamic Programming
This week, you will learn how to compute value functions and optimal policies, assuming you have the MDP model. You will implement dynamic programming to compute value functions and optimal policies and understand the utility of dynamic programming for industrial applications and problems. Further, you will learn about Generalized Policy Iteration as a common template for constructing algorithms that maximize reward. For this week’s graded assessment, you will implement an efficient dynamic programming agent in a simulated industrial control problem.
4 hours to complete
10 videos (Total 72 min), 3 readings, 2 quizzes
10 videos
Iterative Policy Evaluation8m
Policy Improvement4m
Policy Iteration8m
Flexibility of the Policy Iteration Framework4m
Efficiency of Dynamic Programming5m
Warren Powell: Approximate Dynamic Programming for Fleet Management (Short)7m
Warren Powell: Approximate Dynamic Programming for Fleet Management (Long)21m
Week 4 Summary2m
Congratulations!3m
3 readings
Module 4 Learning Objectives10m
Weekly Reading30m
Chapter Summary30m
1 practice exercise
Dynamic Programming45m
Reviews
TOP REVIEWS FROM FUNDAMENTALS OF REINFORCEMENT LEARNING
by AROct 27, 2020
The video lectures were very short and just a repetition of the book itself. After we studied the book, the lectures didn't have anything new for us. They should have been different and more hands-on.
by ATJul 6, 2020
An excellent introduction to Reinforcement Learning, accompanied by a well-organized & informative handbook. I definitely recommend this course to have a strong foundation in Reinforcement Learning.
by AMAug 23, 2020
Don't think it would be unreasonable to have more demanding coding assignments where all functions are made from scratch (though the function names and some comments might be provided as an outline.
by NHApr 7, 2020
This course is one of the best I've learned so far in coursera. The explanations are clear and concise enough. It took a while for me to understand Bellman equation but when I did, it felt amazing!
About the Reinforcement Learning Specialization
The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI).
Frequently Asked Questions
When will I have access to the lectures and assignments?
What will I get if I subscribe to this Specialization?
Is financial aid available?
Will I earn university credit for completing the Course?
More questions? Visit the Learner Help Center.
