Retour à Prediction and Control with Function Approximation

4.8
étoiles
749 évaluations

## À propos du cours

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...

## Meilleurs avis

WP

11 avr. 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 déc. 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.

Filtrer par :

## 1 - 25 sur 133 Avis pour Prediction and Control with Function Approximation

par George G

28 févr. 2020

par Neil H

3 nov. 2021

par Mukund C

27 mars 2020

par Navid H

16 oct. 2019

par Maxim V

23 janv. 2020

par Arthur O

9 oct. 2020

par Maximiliano B

31 mars 2020

par D. R

31 déc. 2019

par Mark J

22 oct. 2019

par Ian W

17 juin 2021

par Julien T

12 nov. 2019

par Gordon L W C

23 mars 2020

par Walter O A

9 déc. 2019

par Stefano P

19 mai 2020

par Sebastian P B

2 déc. 2019

par Zhang d

6 mai 2020

par Jesse W

29 juil. 2020

par Guilherme V

20 nov. 2020

par Tobias L

14 oct. 2020

par Alvaro M A

3 avr. 2020

par Surya K

30 avr. 2020

par César S

8 août 2021

par Lim G

10 mai 2020

par Thomas G

21 avr. 2020

par Mateusz K

29 oct. 2019