In this course, you will learn how to solve problems with large, high-dimensional, and potentially infinite state spaces. You will see that estimating value functions can be cast as a supervised learning problem---function approximation---allowing you to build agents that carefully balance generalization and discrimination in order to maximize reward. We will begin this journey by investigating how our policy evaluation or prediction methods like Monte Carlo and TD can be extended to the function approximation setting. You will learn about feature construction techniques for RL, and representation learning via neural networks and backprop. We conclude this course with a deep-dive into policy gradient methods; a way to learn policies directly without learning a value function. In this course you will solve two continuous-state control tasks and investigate the benefits of policy gradient methods in a continuous-action environment.
Offered By
Reinforcement Learning SpecializationUniversity of AlbertaAbout this Course
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.
Skills you will gain
Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.
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
Welcome to the Course!
Welcome to the third course in the Reinforcement Learning Specialization: Prediction and Control with Function Approximation, brought to you by the University of Alberta, Onlea, and Coursera. In this pre-course module, you'll be introduced to your instructors, and get a flavour of what the course has in store for you. Make sure to introduce yourself to your classmates in the "Meet and Greet" section!
On-policy Prediction with Approximation
This week you will learn how to estimate a value function for a given policy, when the number of states is much larger than the memory available to the agent. You will learn how to specify a parametric form of the value function, how to specify an objective function, and how estimating gradient descent can be used to estimate values from interaction with the world.
Constructing Features for Prediction
The features used to construct the agent’s value estimates are perhaps the most crucial part of a successful learning system. In this module we discuss two basic strategies for constructing features: (1) fixed basis that form an exhaustive partition of the input, and (2) adapting the features while the agent interacts with the world via Neural Networks and Backpropagation. In this week’s graded assessment you will solve a simple but infinite state prediction task with a Neural Network and TD learning.
Control with Approximation
This week, you will see that the concepts and tools introduced in modules two and three allow straightforward extension of classic TD control methods to the function approximation setting. In particular, you will learn how to find the optimal policy in infinite-state MDPs by simply combining semi-gradient TD methods with generalized policy iteration, yielding classic control methods like Q-learning, and Sarsa. We conclude with a discussion of a new problem formulation for RL---average reward---which will undoubtedly be used in many applications of RL in the future.
Policy Gradient
Every algorithm you have learned about so far estimates a value function as an intermediate step towards the goal of finding an optimal policy. An alternative strategy is to directly learn the parameters of the policy. This week you will learn about these policy gradient methods, and their advantages over value-function based methods. You will also learn how policy gradient methods can be used to find the optimal policy in tasks with both continuous state and action spaces.
Reviews
TOP REVIEWS FROM PREDICTION AND CONTROL WITH FUNCTION APPROXIMATION
Surely a level-up from the previous courses. This course adds to and extends what has been learned in courses 1 & 2 to a greater sphere of real-world problems. Great job Prof. Adam and Martha!
I had been reading the book of Reinforcement Learning An Introduction by myself. This class helped me to finish the study with a great learning environment. Thank you, Martha and Adam!
Great Learning, the best part was the Actor-Critic algorithm for a small pendulum swing task all from stratch using RLGLue library. Love to learn how experimentation in RL works.
Good course with a lot of technical information. I would add another assignment or make current ones a little bit more extensive, as there are many concepts to learn.
About the Reinforcement Learning Specialization
Frequently Asked Questions
When will I have access to the lectures and assignments?
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
- The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
- The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
What is the refund policy?
If you subscribed, you get a 7-day free trial during which you can cancel at no penalty. After that, we don’t give refunds, but you can cancel your subscription at any time. See our full refund policy.
Is financial aid available?
Yes, Coursera provides financial aid to learners who cannot afford the fee. Apply for it by clicking on the Financial Aid link beneath the "Enroll" button on the left. You'll be prompted to complete an application and will be notified if you are approved. You'll need to complete this step for each course in the Specialization, including the Capstone Project. Learn more.
Will I earn university credit for completing the Course?
This Course doesn't carry university credit, but some universities may choose to accept Course Certificates for credit. Check with your institution to learn more. Online Degrees and Mastertrack™ Certificates on Coursera provide the opportunity to earn university credit.
More questions? Visit the Learner Help Center.
