About this Course

37,280 recent views
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
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. 23 hours to complete
English

Skills you will gain

Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
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. 23 hours to complete
English

Offered by

Placeholder

University of Alberta

Placeholder

Alberta Machine Intelligence Institute

Syllabus - What you will learn from this course

Week
1

Week 1

1 hour to complete

Welcome to the Final Capstone Course!

1 hour to complete
2 videos (Total 10 min), 2 readings
2 videos
Meet your instructors!8m
2 readings
Reinforcement Learning Textbook10m
Pre-requisites and Learning Objectives10m
Week
2

Week 2

1 hour to complete

Milestone 1: Formalize Word Problem as MDP

1 hour to complete
4 videos (Total 23 min)
4 videos
Andy Barto on What are Eligibility Traces and Why are they so named?9m
Let's Review: Markov Decision Processes6m
Let's Review: Examples of Episodic and Continuing Tasks3m
Week
3

Week 3

1 hour to complete

Milestone 2: Choosing The Right Algorithm

1 hour to complete
7 videos (Total 40 min)
7 videos
Let's Review: Expected Sarsa3m
Let's Review: What is Q-learning?3m
Let's Review: Average Reward- A New Way of Formulating Control Problems10m
Let's Review: Actor-Critic Algorithm5m
Csaba Szepesvari on Problem Landscape8m
Andy and Rich: Advice for Students5m
1 practice exercise
Choosing the Right Algorithm
Week
4

Week 4

1 hour to complete

Milestone 3: Identify Key Performance Parameters

1 hour to complete
4 videos (Total 25 min)
4 videos
Let's Review: Non-linear Approximation with Neural Networks4m
Drew Bagnell on System ID + Optimal Control6m
Susan Murphy on RL in Mobile Health7m
1 practice exercise
Impact of Parameter Choices in RL40m

Reviews

TOP REVIEWS FROM A COMPLETE REINFORCEMENT LEARNING SYSTEM (CAPSTONE)

View all reviews

About the Reinforcement Learning Specialization

Reinforcement Learning

Frequently Asked Questions

More questions? Visit the Learner Help Center.