Chevron Left
Back to Sample-based Learning Methods

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

4.7
stars
949 ratings
193 reviews

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

AA
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

KM
Jan 9, 2020

Really great resource to follow along the RL Book. IMP Suggestion: Do not skip the reading assignments, they are really helpful and following the videos and assignments becomes easy.

Filter by:

151 - 175 of 189 Reviews for Sample-based Learning Methods

By Yicong H

Dec 4, 2019

Jump for here to there, it's nice to have all these algorithms. My gut tells me something is not correct. Too much focus on experience, which means a lot of data. The model part is touched very little, and main focus is on when model is wrong.....

By Arun A

Sep 22, 2020

Mid way thru my course in week 5, Jupyter notebooks were revised. In general, new ones are better but lost valuable forum discussion Still one error in plot of notebook of week 5th. But in general course was good

By Matias x

Jun 8, 2020

This is a very good course, the only thing to improve are the technical issues with the assignments and submission processes. I had problems on the half of the assignments and many others learners too.

By Narendra G

Jun 26, 2020

It's an important course in understanding the working of reinforcement learning. Although some important and complex topics are not explored in this course which are mentioned in the textbook.

By Misael D C

Jun 30, 2020

This course excellent, my only complaint is that there is a 5 attempts limits and a 4 months wait to retry. It seems excesive to me and adds extra pressure when taking on assignments.

By István Z K

May 21, 2020

Overall a very nice course, well explained and presented.

Sometimes, it would be nice to see the slides 'full screen' rather than the small version in the corner.

By Sebastian T

Feb 28, 2020

I

t

w

a

s

g

o

o

d

i

n

s

u

b

s

t

a

n

e but there is plenty of issues with the automated grader. you spend most time dealing with the letter not on actual learning of the matter.

By Bruno L

May 21, 2020

The lectures and quiz tests are perfect. Jupyter. Programming exercises can be a little confusing sometimes but are also great. A great course, overall.

By Navid H

Oct 16, 2019

definitely interesting subjects, but I do not like the teaching method. Very mechanic and dull, with not enough connection to the real world

By Bhargav D P

Jul 1, 2020

Everything is great overall but It would be more better if DynaQ & DynaQ+ were explained more detail in the lecture instead of assignment.

By Wahyu G

Mar 20, 2020

Pretty clear explanations! Nice starting point if you want to deep dive into RL. It gives clear picture over some confusing terms in RL.

By judson g

Aug 21, 2020

Assignment problems needs to be clearly defined and content of the video needs to updated and expects more information

By Cristian V

Mar 30, 2020

The course provides a lot of value. I only give 4 stars because the classes are scripted and feel unnatural to me.

By Max C

Oct 23, 2019

Some of the programming homeworks were difficult to debug due to the feedback from autograder being unhelpful.

By Rajvardhan P

Dec 8, 2020

Would recommend covering more examples to aid the understanding of concepts.

By Hugo T K

Aug 11, 2020

The course is excellent! Only missed some programming assignments on Week 2.

By Nicolas M

Sep 23, 2020

Great course, but some exercises would be better using concrete examples.

By Soren J

Jun 20, 2020

Very good. Although the python skills are quite high to pass this course.

By Yu G

Jan 21, 2021

Tough, challenging course, very worthwhile taking!

By Sachin K

Aug 17, 2020

Passing notebook assignments is hellish due to strict decimal matching for numerical computations. You must do steps in one specific order or the assignments in autograder comparisons won't work. The course is itself fine and is more or less a rehash of the book so you may as well read that. There is no special intuition but the notebooks do provide a good experimental design strategy. Many of the experiments listed in the book are actually implemented in assignments which aids in learning. There is no technical support staff on Coursera anymore. So you are on your own when taking the course. Discussions forums are littered with discussion prompts and new ones are added every week so its not easy to find anything in there. Coursera has become substandard and the rating reflects a mixture of the course and coursera as a platform.

By Mark L

Jul 1, 2020

This course has presented a large number of techniques/algorithms in addition to the ones presented in the first course. I find it hard to keep track of these. It would be most helpful if the techniques could be summarized in a table to lists the various attributes. In addition, I would like to see some examples of practical problems that can be solved with these techniques in addition to the explanatory "toy" problems. I also find the pace of the lectures a little "choppy", with a lot of very small lectures, each with its own introduction and summary.

By Hadrien H

Dec 13, 2020

Still very good course but I felt like this second unit covers less of the book than the first one. The classes are quite shorter than in the first part while the book content gets richer. The assignments are a bit more complete though

By Mukesh

Sep 11, 2020

There should be more examples on Q-learning and Expected SARSA. The course just compares different algorithms for different parameters. The autograder is annoying too. Really need some work on that. Otherwise the course is okay.

By Alessandro o

Jun 12, 2020

To be honest I think that arguments quite complex are treated too quickly and basically it's up to you to figure it out. I think that some ideas would have been nice to have a more detailed explanation

By Juan A V G

Apr 13, 2021

It is required some mentoring on the Discussion forums. There is some part grading part that requires some improvement and it is too dependent on other students to work around some main issues.