Chevron Left
Volver a Sample-based Learning Methods

Opiniones y comentarios de aprendices correspondientes a Sample-based Learning Methods por parte de Universidad de Alberta

1,146 calificaciones

Acerca del Curso

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...

Principales reseñas


14 de feb. de 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.


11 de ago. de 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

Filtrar por:

51 - 75 de 222 revisiones para Sample-based Learning Methods

por Art H

13 de abr. de 2020

Well done. Follows Reinforcement Learning (Sutton/Barto) closely and explains topics well. Graded notebooks are invaluable in understanding the material well.

por Kees J d V

19 de dic. de 2020

Reinforcement Learning has added a whole new paradigm to my thinking. The course + book combination is perfect. The instructors are extremely good :D

por Karim D

20 de oct. de 2020

Excellent course. Really well taught. Good pace of videos and assignments, with the support of perfect reading material. thank you tot he teachers.

por Giulio C

13 de jul. de 2020

Excellent course and instructors! I'm very excited about this specialization. They are able to explain hard concepts from the book in an easy way.

por Umut Z

23 de nov. de 2019

Good balance of theory and programming assignments. I really like the weekly bonus videos with professors and developers. Recommend to everyone.

por Danish A

4 de jul. de 2022

Excellent paced course that helped me understand sample based methods. Assignments were thoroughly build to practically utilize these concepts

por Tianpei X

8 de ago. de 2022

This coures is part of Reinforcement Learning specialization. You need to understand basic statistics to understand it. Good instruction !


19 de abr. de 2020

One of most accurate, precise and well explained courses I have ever had with Coursera. Congratulations for teachers and course creators.

por 李谨杰

1 de may. de 2020

An excellent course!!!! This is the best course I have ever taken on Coursera! Thanks a lot to two supervisors and teaching assistants!

por Leon Y

9 de ene. de 2021

Awesome videos and homework! Great thanks to Prof. Martha White and Prof. Adam White! I do appreciate such educational opportunities!

por S. K G P

11 de jun. de 2020

I think it was one of the best courses to cover this topic. Clear and crisp presentations. Great programming assignments as well!!

por Christian J R F

7 de may. de 2020

Excelent course, I would love to do some other exercises out of the grid world but in general the content is good and interesting.

por Pokman C

8 de abr. de 2021

Concepts and methods introduced in this course are well motivated and presented. The assignments are very thoughtfully designed.

por Antonis S

9 de may. de 2020

Very well prepared and interesting course! I will seek more for sure in the future! Thank you so much for offering this course!

por La W N

28 de jul. de 2020

I am really enjoying to learn reinforcement learning. The instructors are really good at explanation. Going for next course B)

por Kiara O

7 de ene. de 2020

This course is well explained, easy to follow and made me understand much better the tabular RL methods. I liked it very much.

por John J

28 de abr. de 2020

This second instalment in the reinforcement learning journey is amazing. Although you can get stuck sometimes in some places.

por nicole s

2 de feb. de 2020

I like the teaching style the emphasis on understanding and the fruitful combination with the textbook. Highly recommended!

por Nikhil G

25 de nov. de 2019

Excellent course companion to the textbook, clarifies many of the vague topics and gives good tests to ensure understanding

por Johannes

10 de sep. de 2021

Enlightening explanations, well-structured content and challenging assignments. Very engaging course I thoroughly enjoyed!

por Nathaniel W

24 de dic. de 2020

Well done course that covers the different basic aspects of to do reinforcement learning and how models work into it.

por Lik M C

10 de ene. de 2020

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

por Zhang d

7 de abr. de 2020

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

por Xingbei W

8 de mar. de 2020

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

por Mathew

7 de jun. de 2020

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