Chevron Left
Zurück zu Prediction and Control with Function Approximation

Bewertung und Feedback des Lernenden für Prediction and Control with Function Approximation von University of Alberta

4.8
Sterne
731 Bewertungen

Über den Kurs

In this course, you will learn how to solve problems with large, high-dimensional, and potentially infinite state spaces. You will see that estimating value functions can be cast as a supervised learning problem---function approximation---allowing you to build agents that carefully balance generalization and discrimination in order to maximize reward. We will begin this journey by investigating how our policy evaluation or prediction methods like Monte Carlo and TD can be extended to the function approximation setting. You will learn about feature construction techniques for RL, and representation learning via neural networks and backprop. We conclude this course with a deep-dive into policy gradient methods; a way to learn policies directly without learning a value function. In this course you will solve two continuous-state control tasks and investigate the benefits of policy gradient methods in a continuous-action environment. Prerequisites: This course strongly builds on the fundamentals of Courses 1 and 2, and learners should have completed these before starting this course. Learners should also be comfortable with probabilities & expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), and implementing algorithms from pseudocode. By the end of this course, you will be able to: -Understand how to use supervised learning approaches to approximate value functions -Understand objectives for prediction (value estimation) under function approximation -Implement TD with function approximation (state aggregation), on an environment with an infinite state space (continuous state space) -Understand fixed basis and neural network approaches to feature construction -Implement TD with neural network function approximation in a continuous state environment -Understand new difficulties in exploration when moving to function approximation -Contrast discounted problem formulations for control versus an average reward problem formulation -Implement expected Sarsa and Q-learning with function approximation on a continuous state control task -Understand objectives for directly estimating policies (policy gradient objectives) -Implement a policy gradient method (called Actor-Critic) on a discrete state environment...

Top-Bewertungen

WP

11. Apr. 2020

Difficult but excellent and impressing. Human being is incredible creating such ideas. This course shows a way to the state when all such ingenious ideas will be created by self learning algorithms.

AC

1. Dez. 2019

Well peaced and thoughtfully explained course. Highly recommended for anyone willing to set solid grounding in Reinforcement Learning. Thank you Coursera and Univ. of Alberta for the masterclass.

Filtern nach:

51 - 75 von 133 Bewertungen für Prediction and Control with Function Approximation

von Andrew G

26. Jan. 2020

von Alexander P

14. Dez. 2019

von Mathew

7. Juni 2020

von Ayan S

4. Juli 2021

von Johannes

13. Sep. 2021

von Joosung M

14. Juni 2020

von Tolga K

25. Dez. 2020

von J B

13. Okt. 2020

von LI C Y

14. Aug. 2022

von Eduardo I L H

14. Jan. 2021

von Yitao H

29. Aug. 2021

von Huang C

25. Jan. 2022

von RICARDO A F S

21. Nov. 2020

von Artur M

3. Nov. 2020

von George M

11. März 2021

von Chang, W C

14. Okt. 2019

von Rishi R

3. Aug. 2020

von Kaustubh S

24. Dez. 2019

von Max C

1. Nov. 2019

von Sergey M

15. Okt. 2021

von Saulo A G S

12. Aug. 2022

von LIWANGZHI

27. Jan. 2020

von Pachi C

31. Dez. 2019

von 석박통합김한준

25. Apr. 2020

von Raktim P

17. Dez. 2019