74,595 次近期查看

1

## Intro: why should i care?

In this module we gonna define and "taste" what reinforcement learning is about. We'll also learn one simple algorithm that can solve reinforcement learning problems with embarrassing efficiency.

...
13 個視頻 （總計 84 分鐘）, 8 個閱讀材料, 3 個測驗
13 個視頻
Reinforcement learning vs all3分鐘
Multi-armed bandit4分鐘
Decision process & applications6分鐘
Markov Decision Process5分鐘
Crossentropy method9分鐘
Approximate crossentropy method5分鐘
More on approximate crossentropy method6分鐘
Evolution strategies: core idea6分鐘
Evolution strategies: math problems5分鐘
Evolution strategies: log-derivative trick8分鐘
Evolution strategies: duct tape6分鐘
Blackbox optimization: drawbacks4分鐘
8 個閱讀材料
What you're getting into1分鐘
Setting up course environment10分鐘
Note: this course vs github course1分鐘
Lecture slides10分鐘
Course teaser placeholder10分鐘
Primers1分鐘
Extras10分鐘
2

## At the heart of RL: Dynamic Programming

This week we'll consider the reinforcement learning formalisms in a more rigorous, mathematical way. You'll learn how to effectively compute the return your agent gets for a particular action - and how to pick best actions based on that return.

...
5 個視頻 （總計 54 分鐘）, 2 個閱讀材料, 4 個測驗
5 個視頻
State and Action Value Functions13分鐘
Measuring Policy Optimality6分鐘
Policy: evaluation & improvement10分鐘
Policy and value iteration8分鐘
2 個閱讀材料
Discrete Stochastic Dynamic Programming10分鐘
3 個練習
Reward design8分鐘
Optimality in RL10分鐘
Policy Iteration14分鐘
3

## Model-free methods

This week we'll find out how to apply last week's ideas to the real world problems: ones where you don't have a perfect model of your environment.

...
6 個視頻 （總計 47 分鐘）, 1 個閱讀材料, 4 個測驗
6 個視頻
Monte-Carlo & Temporal Difference; Q-learning8分鐘
Exploration vs Exploitation8分鐘
Footnote: Monte-Carlo vs Temporal Difference2分鐘
Accounting for exploration. Expected Value SARSA.11分鐘
On-policy vs off-policy; Experience replay7分鐘
1 個閱讀材料
Extras10分鐘
1 個練習
Model-free reinforcement learning10分鐘
4

## Approximate Value Based Methods

This week we'll learn to scale things even farther up by training agents based on neural networks.

...
9 個視頻 （總計 104 分鐘）, 3 個閱讀材料, 5 個測驗
9 個視頻
Loss functions in value based RL11分鐘
Difficulties with Approximate Methods15分鐘
DQN – bird's eye view9分鐘
DQN – the internals9分鐘
DQN: statistical issues6分鐘
Double Q-learning6分鐘
More DQN tricks10分鐘
Partial observability17分鐘
3 個閱讀材料
TD vs MC10分鐘
Extras10分鐘
DQN follow-ups10分鐘
3 個練習
MC & TD8分鐘
SARSA and QLeaning8分鐘
DQN12分鐘
4.1
56 個審閱

## 33%

### 來自Practical Reinforcement Learning的熱門評論

This is one of the Best Course available on Reinforcement Learning. I have gone through various study material but the depth and practical knowledge given in the course is awesome.

A great course with very practical assignments to help you learn how to implement RL algorithms. But it also has some stupid quiz questions which makes you feel confusing.

## 講師

### Pavel Shvechikov

Researcher at HSE and Sberbank AI Lab
HSE Faculty of Computer Science

### Alexander Panin

Lecturer
HSE Faculty of Computer Science

## 關於 国立高等经济大学

National Research University - Higher School of Economics (HSE) is one of the top research universities in Russia. Established in 1992 to promote new research and teaching in economics and related disciplines, it now offers programs at all levels of university education across an extraordinary range of fields of study including business, sociology, cultural studies, philosophy, political science, international relations, law, Asian studies, media and communicamathematics, engineering, and more. Learn more on www.hse.ru...

## 關於 高级机器学习 專項課程

This specialization gives an introduction to deep learning, reinforcement learning, natural language understanding, computer vision and Bayesian methods. Top Kaggle machine learning practitioners and CERN scientists will share their experience of solving real-world problems and help you to fill the gaps between theory and practice. Upon completion of 7 courses you will be able to apply modern machine learning methods in enterprise and understand the caveats of real-world data and settings....

## 常見問題

• 注册以便获得证书后，您将有权访问所有视频、测验和编程作业（如果适用）。只有在您的班次开课之后，才可以提交和审阅同学互评作业。如果您选择在不购买的情况下浏览课程，可能无法访问某些作业。

• 您注册课程后，将有权访问专项课程中的所有课程，并且会在完成课程后获得证书。您的电子课程证书将添加到您的成就页中，您可以通过该页打印您的课程证书或将其添加到您的领英档案中。如果您只想阅读和查看课程内容，可以免费旁听课程。