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:

101 - 125 de 222 revisiones para Sample-based Learning Methods

por leftheory

6 de jul. de 2021

Very neat and clear. However, it just follows the RL book strictly.

por Varun K R K

15 de may. de 2021

The best course available on entire world for reinforcement learning

por Dan N

24 de oct. de 2021

I liked that this course had programming assignments for each week.

por Animesh

28 de may. de 2020

this course is very well designed and executed. wow! i loved it :D

por Li W

30 de mar. de 2020

Very good introductions and practices to the classic RL algorithms

por DEEP P

8 de jul. de 2020

Great learning Experience and really helpful lecturers and staff.

por Rudi C

21 de jul. de 2020

Wonderful course, highly instructive, and follows the textbook!

por Rajesh

2 de jul. de 2020

Please make assignments more explanatory and allow flexiblity

por Farzad E b

28 de jul. de 2022

It was great!! One of the best courses I've ever enrolled in

por alper d

17 de ene. de 2021

Good course material and simplified explanations. Thank you.

por Da

3 de nov. de 2019

Really a wonderful course! Very professional and high level.

por Teresa Y B

10 de abr. de 2020

Very well structured course, Thanks for so nice preparing!!

por Shi Y

10 de nov. de 2019


por Alex E

19 de nov. de 2019

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

por Jicheng F

11 de jul. de 2020

Martha and Adam are great instructors, great job!

por garcia b

31 de dic. de 2019

very copacetic. excellent complement to the book

por Ignacio O

13 de oct. de 2019

Great, informative and very interesting course.

por Ashish S

16 de sep. de 2019

A good course with proper Mathematical insights

por Guruprasad

13 de jul. de 2021

very intutive and the instructors are succinct

por Cheuk L Y

3 de jul. de 2020

Very good overall! It takes time to digest.


15 de ene. de 2020

A nice course with well-designed homework:)

por Jingxin X

26 de may. de 2020

Very helpful follow up tot he first one.

por Ryan Y

17 de ene. de 2021

Better than reading the textbook alone.

por Sriram R

20 de oct. de 2019

Well done mix of theory and practice!

por Luiz C

13 de sep. de 2019

Great Course. Every aspect top notch