Chevron Left
Zurück zu Sample-based Learning Methods

Bewertung und Feedback des Lernenden für Sample-based Learning Methods von University of Alberta

4.8
Sterne
1,136 Bewertungen

Über den Kurs

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-Bewertungen

DP

14. Feb. 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.

AA

11. Aug. 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

Filtern nach:

1 - 25 von 221 Bewertungen für Sample-based Learning Methods

von JD

22. Sep. 2019

von Kaiwen Y

2. Okt. 2019

von hope

25. Jan. 2020

von Juan C E

7. März 2020

von Rishi R

3. Aug. 2020

von Mukund C

17. März 2020

von Kinal M

10. Jan. 2020

von Kyle A

3. Okt. 2019

von Ivan S F

29. Sep. 2019

von Manuel B

28. Nov. 2019

von Amit J

27. Feb. 2021

von Manuel V d S

4. Okt. 2019

von Maxim V

12. Jan. 2020

von Andrew G

24. Dez. 2019

von Bernard C

22. März 2020

von Maximiliano B

23. Feb. 2020

von Jonathan B

9. Mai 2020

von Steven W

11. Mai 2021

von Sandesh J

8. Juni 2020

von César S

9. Juli 2021

von Yover M C C

22. Apr. 2020

von Alberto H

28. Okt. 2019

von Karol P

9. Apr. 2021

von Pars V

5. Jan. 2020

von Surya K

12. Apr. 2020