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.

제공자:

## About this Course

### 귀하가 습득할 기술

#### 100% 온라인

#### 다음 전문 분야의 4개 강좌 중 3번째 강좌:

#### 유동적 마감일

#### 중급 단계

Probabilities & Expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), implementing algorithms from pseudocode.

#### 완료하는 데 약 18시간 필요

#### 영어

## 강의 계획 - 이 강좌에서 배울 내용

**완료하는 데 1시간 필요**

## Welcome to the Course!

Welcome to the third course in the Reinforcement Learning Specialization: Prediction and Control with Function Approximation, brought to you by the University of Alberta, Onlea, and Coursera. In this pre-course module, you'll be introduced to your instructors, and get a flavour of what the course has in store for you. Make sure to introduce yourself to your classmates in the "Meet and Greet" section!

**완료하는 데 1시간 필요**

**2개의 읽기 자료**

**완료하는 데 6시간 필요**

## On-policy Prediction with Approximation

This week you will learn how to estimate a value function for a given policy, when the number of states is much larger than the memory available to the agent. You will learn how to specify a parametric form of the value function, how to specify an objective function, and how estimating gradient descent can be used to estimate values from interaction with the world.

**완료하는 데 6시간 필요**

**13개의 동영상**

**1개의 읽기 자료**

**1개 연습문제**

**완료하는 데 8시간 필요**

## Constructing Features for Prediction

The features used to construct the agent’s value estimates are perhaps the most crucial part of a successful learning system. In this module we discuss two basic strategies for constructing features: (1) fixed basis that form an exhaustive partition of the input, and (2) adapting the features while the agent interacts with the world via Neural Networks and Backpropagation. In this week’s graded assessment you will solve a simple but infinite state prediction task with a Neural Network and TD learning.

**완료하는 데 8시간 필요**

**11개의 동영상**

**1개의 읽기 자료**

**1개 연습문제**

**완료하는 데 8시간 필요**

## Control with Approximation

This week, you will see that the concepts and tools introduced in modules two and three allow straightforward extension of classic TD control methods to the function approximation setting. In particular, you will learn how to find the optimal policy in infinite-state MDPs by simply combining semi-gradient TD methods with generalized policy iteration, yielding classic control methods like Q-learning, and Sarsa. We conclude with a discussion of a new problem formulation for RL---average reward---which will undoubtedly be used in many applications of RL in the future.

**완료하는 데 8시간 필요**

**7개의 동영상**

**1개의 읽기 자료**

**1개 연습문제**

**완료하는 데 6시간 필요**

## Policy Gradient

Every algorithm you have learned about so far estimates a value function as an intermediate step towards the goal of finding an optimal policy. An alternative strategy is to directly learn the parameters of the policy. This week you will learn about these policy gradient methods, and their advantages over value-function based methods. You will also learn how policy gradient methods can be used to find the optimal policy in tasks with both continuous state and action spaces.

**완료하는 데 6시간 필요**

**11개의 동영상**

**1개의 읽기 자료**

**1개 연습문제**

### 검토

#### 4.8

##### PREDICTION AND CONTROL WITH FUNCTION APPROXIMATION의 최상위 리뷰

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.

Great Learning, the best part was the Actor-Critic algorithm for a small pendulum swing task all from stratch using RLGLue library. Love to learn how experimentation in RL works.

Good course with a lot of technical information. I would add another assignment or make current ones a little bit more extensive, as there are many concepts to learn.

Great course. Slightly more complex than courses 1 and 2, but a huge improvement in terms of applicability to real-world situations.

### 제공자:

#### 앨버타 대학교

UAlberta is considered among the world’s leading public research- and teaching-intensive universities. As one of Canada’s top universities, we’re known for excellence across the humanities, sciences, creative arts, business, engineering and health sciences.

#### Alberta Machine Intelligence Institute

The Alberta Machine Intelligence Institute (Amii) is home to some of the world’s top talent in machine intelligence. We’re an Alberta-based

## 강화 학습 전문 분야 정보

## 자주 묻는 질문

강의 및 과제를 언제 이용할 수 있게 되나요?

강좌에 등록하면 바로 모든 비디오, 테스트 및 프로그래밍 과제(해당하는 경우)에 접근할 수 있습니다. 상호 첨삭 과제는 이 세션이 시작된 경우에만 제출하고 검토할 수 있습니다. 강좌를 구매하지 않고 살펴보기만 하면 특정 과제에 접근하지 못할 수 있습니다.

이 전문 분야를 구독하면 무엇을 이용할 수 있나요?

강좌를 등록하면 전문 분야의 모든 강좌에 접근할 수 있고 강좌를 완료하면 수료증을 취득할 수 있습니다. 전자 수료증이 성취도 페이지에 추가되며 해당 페이지에서 수료증을 인쇄하거나 LinkedIn 프로필에 수료증을 추가할 수 있습니다. 강좌 내용만 읽고 살펴보려면 해당 강좌를 무료로 청강할 수 있습니다.

환불 규정은 어떻게 되나요?

재정 지원을 받을 수 있나요?

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.