Chevron Left
Voltar para Prediction and Control with Function Approximation

Comentários e feedback de alunos de Prediction and Control with Function Approximation da instituição Universidade de AlbertaUniversidade de Alberta

4.8
estrelas
749 classificações

Sobre o curso

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...

Melhores avaliações

WP

11 de abr de 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 de dez de 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.

Filtrar por:

1 — 25 de 133 Avaliações para o Prediction and Control with Function Approximation

por George G

28 de fev de 2020

por Neil H

3 de nov de 2021

por Mukund C

27 de mar de 2020

por Navid H

16 de out de 2019

por Maxim V

23 de jan de 2020

por Arthur O

9 de out de 2020

por Maximiliano B

31 de mar de 2020

por D. R

31 de dez de 2019

por Mark J

22 de out de 2019

por Ian W

17 de jun de 2021

por Julien T

12 de nov de 2019

por Gordon L W C

23 de mar de 2020

por Walter O A

9 de dez de 2019

por Stefano P

19 de mai de 2020

por Sebastian P B

2 de dez de 2019

por Zhang d

6 de mai de 2020

por Jesse W

29 de jul de 2020

por Guilherme V

20 de nov de 2020

por Tobias L

14 de out de 2020

por Alvaro M A

3 de abr de 2020

por Surya K

30 de abr de 2020

por César S

8 de ago de 2021

por Lim G

10 de mai de 2020

por Thomas G

21 de abr de 2020

por Mateusz K

29 de out de 2019