Chevron Left
返回到 Prediction and Control with Function Approximation

学生对 阿尔伯塔大学 提供的 Prediction and Control with Function Approximation 的评价和反馈

4.8
731 个评分

课程概述

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...

热门审阅

WP

Apr 11, 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

Dec 1, 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.

筛选依据:

101 - Prediction and Control with Function Approximation 的 125 个评论(共 133 个)

创建者 PHILIP C

Jun 18, 2021

创建者 Luiz C

Oct 3, 2019

创建者 Luka K

Jan 4, 2021

创建者 Dmitry S

Jan 5, 2020

创建者 Hadrien H

Feb 4, 2021

创建者 Steven W

May 11, 2021

创建者 Narendra G

Jul 19, 2020

创建者 Nicolas M

Oct 24, 2020

创建者 Lucas O S

Jan 21, 2020

创建者 Anirban D

Jul 24, 2022

创建者 남상혁

Jan 17, 2021

创建者 Hugo V

Jan 15, 2020

创建者 Amit J

Mar 17, 2021

创建者 Lik M C

Jan 18, 2020

创建者 Mark P

Aug 17, 2020

创建者 Anton P

Apr 12, 2020

创建者 Vladyslav Y

Sep 8, 2020

创建者 Sharang P

Feb 27, 2020

创建者 Jerome b

Apr 9, 2020

创建者 Rajesh M

Apr 17, 2020

创建者 SCOTT A

Aug 5, 2020

创建者 Muhammed A Ç

Sep 4, 2021

创建者 Pouya E

Dec 2, 2020

创建者 Rishabh K

May 19, 2020

创建者 Ramaz J

Oct 17, 2019