Chevron Left
返回到 Sample-based Learning Methods

學生對 阿尔伯塔大学 提供的 Sample-based Learning Methods 的評價和反饋

711 個評分
149 條評論


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...



Aug 12, 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


Jan 10, 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.


76 - Sample-based Learning Methods 的 100 個評論(共 145 個)

創建者 Shi Y

Nov 10, 2019


創建者 Alex E

Nov 19, 2019

A fun an interesting course. Keep up the great work!

創建者 Jicheng F

Jul 11, 2020

Martha and Adam are great instructors, great job!

創建者 garcia b

Dec 31, 2019

very copacetic. excellent complement to the book

創建者 Ignacio O

Oct 13, 2019

Great, informative and very interesting course.

創建者 Ashish S

Sep 16, 2019

A good course with proper Mathematical insights

創建者 Cheuk L Y

Jul 03, 2020

Very good overall! It takes time to digest.


Jan 15, 2020

A nice course with well-designed homework:)

創建者 Jingxin X

May 27, 2020

Very helpful follow up tot he first one.

創建者 Sriram R

Oct 21, 2019

Well done mix of theory and practice!

創建者 Luiz C

Sep 13, 2019

Great Course. Every aspect top notch

創建者 Alejandro D

Sep 19, 2019

Excellent content and delivery.

創建者 Bekay K

Jul 05, 2020

Great resource to learning RL


Jun 01, 2020

Great Course by great faculty!

創建者 Daniel W

Jul 18, 2020

Hard but a really good course

創建者 Pachi C

Dec 08, 2019

Great and fantastic course!!!

創建者 rashid K

Nov 12, 2019

Best RL course ever done

創建者 Eleni F

Mar 15, 2020

i really enjoy it!


Aug 07, 2020

Brilliant Course!

創建者 Julio E F

Jun 29, 2020

Amazing course!

創建者 Santiago M C

May 21, 2020

excelent course

創建者 Tran Q M

Feb 17, 2020

wondrous course

創建者 Ricardo A F S

Sep 06, 2020

Great course

創建者 Antonio P

Dec 13, 2019

Great Course