Chevron Left
Back to Sample-based Learning Methods

Learner Reviews & Feedback for Sample-based Learning Methods by University of Alberta

4.8
stars
1,228 ratings

About the Course

In this course, you will learn about several algorithms that can learn near optimal policies based on trial and error interaction with the environment---learning from the agent’s own experience. Learning from actual experience is striking because it requires no prior knowledge of the environment’s dynamics, yet can still attain optimal behavior. We will cover intuitively simple but powerful Monte Carlo methods, and temporal difference learning methods including Q-learning. We will wrap up this course investigating how we can get the best of both worlds: algorithms that can combine model-based planning (similar to dynamic programming) and temporal difference updates to radically accelerate learning. By the end of this course you will be able to: - Understand Temporal-Difference learning and Monte Carlo as two strategies for estimating value functions from sampled experience - Understand the importance of exploration, when using sampled experience rather than dynamic programming sweeps within a model - Understand the connections between Monte Carlo and Dynamic Programming and TD. - Implement and apply the TD algorithm, for estimating value functions - Implement and apply Expected Sarsa and Q-learning (two TD methods for control) - Understand the difference between on-policy and off-policy control - Understand planning with simulated experience (as opposed to classic planning strategies) - Implement a model-based approach to RL, called Dyna, which uses simulated experience - Conduct an empirical study to see the improvements in sample efficiency when using Dyna...

Top reviews

DP

Feb 14, 2021

Excellent course that naturally extends the first specialization course. The application examples in programming are very good and I loved how RL gets closer and closer to how a living being thinks.

AS

Aug 11, 2020

Great course, giving it 5 stars though it deserves both because the assignments have some serious issues that shouldn't actually be a matter. All the other parts are amazing though. Good job

Filter by:

76 - 100 of 238 Reviews for Sample-based Learning Methods

By Lik M C

Jan 10, 2020

Again, the course is excellent. The assignments are even better than Course 1. A really great course worth to take!

By Zhang d

Apr 7, 2020

It is a wonderful and meanningful course, which can teach us the knowledge of Q-learning, expected Sarsa and so on.

By Xingbei W

Mar 8, 2020

Although I have learned q learning and td, this course still give me a lot of new feeling and understanding on it.

By Mathew

Jun 7, 2020

Very well structured and a great compliment to the Reinforcement Learning (2nd Edition) book by Sutton and Barto.

By George M

Feb 24, 2021

Very well defined course.

Exercises are fairly challenging and provide useful intuition into common problems.

By Alaaeldin Z

Dec 10, 2020

The course is amazing. The lectures are well organized. Quizes and assignments are very useful for learning.

By maryam t

Nov 16, 2021

A very good course for understanding basic concepts of RL. It is not enough for doing projects with coding.

By Stewart A

Sep 3, 2019

Great course! Lots of hands-on RL algorithms. I'm looking forward to the next course in the specialization.

By Casey S S

Feb 11, 2021

I thought this was an excellent sequel, introducing the reader to the fundamental innovations of RL.

By Martin P

May 30, 2020

A very interesting topic presented in an easy to consume form. It was fun learning with this course.

By 김한준

Apr 7, 2020

The course is spectacular! I've learned countless material on Reinforcement learning! Thank you!

By Roberto M

Mar 28, 2020

The course is well organized and teachers provide a lot of examples to facilitate comprehension.

By Chintan K

Jul 22, 2020

the course videos were short and precise , which makes the learning content fun and informative

By Wang G

Oct 19, 2019

Very Nice Explanation and Assignment! Look forward the next 2 courses in this specialization!

By Sodagreenmario

Sep 18, 2019

Great course, but there are still some little bugs that can be fixed in notebook assignments.

By Floris v R

Jan 4, 2022

Very clear explanations in the videos, good tests & asignments. Complex stuff well explained

By Chris D

Apr 18, 2020

Very good. Minor issues with inconsistency between parameter naming in different exercises.

By Alden C

Nov 2, 2022

Compressing this much complication into such a tight package is a tremendous achievement.

By Sirusala N S

Jul 30, 2020

The concepts were explained very clearly. The assignments were helpful in understanding.

By 高橋耕司

Oct 6, 2019

I made a lot of mistakes, but I learned a lot because of that.

It ’s a wonderful course.

By Sérgio V C

Mar 15, 2021

A good course to learn the basics of Monte Carlo methods for RL, as well as TD-methods!

By Jau-Jie Y

Jul 7, 2021

I am happy of the history talking of Barto and Sutton.

The others teachers were good.

By Louis S

Jun 5, 2020

Excellent content. The fact that it follows Sutton and Barto's TextBook is a must.

By Pruthvi J

Feb 7, 2021

Excellent course, gives a decent theoretical and practical introduction to RL.

By Corey A

Apr 19, 2022

Awesome course. Fun examples and exercises and great compliment to the book.