Welcome to the Reinforcement Learning course. Here you will find out about: - foundations of RL methods: value/policy iteration, q-learning, policy gradient, etc. --- with math & batteries included - using deep neural networks for RL tasks --- also known as "the hype train" - state of the art RL algorithms --- and how to apply duct tape to them for practical problems. - and, of course, teaching your neural network to play games --- because that's what everyone thinks RL is about. We'll also use it for seq2seq and contextual bandits. Jump in. It's gonna be fun! Do you have technical problems? Write to us: coursera@hse.ru
提供方
教学大纲 - 您将从这门课程中学到什么
周
1完成时间为 5 小时
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 个视频 （总计 84 分钟）, 8 个阅读材料, 3 个测验
13 个视频
Reinforcement learning vs all3分钟
Multi-armed bandit4分钟
Decision process & applications6分钟
Markov Decision Process5分钟
Crossentropy method9分钟
Approximate crossentropy method5分钟
More on approximate crossentropy method6分钟
Evolution strategies: core idea6分钟
Evolution strategies: math problems5分钟
Evolution strategies: log-derivative trick8分钟
Evolution strategies: duct tape6分钟
Blackbox optimization: drawbacks4分钟
8 个阅读材料
What you're getting into1分钟
Setting up course environment10分钟
Note: this course vs github course1分钟
Lecture slides10分钟
Course teaser placeholder10分钟
Primers1分钟
About honors track1分钟
Extras10分钟
周
2完成时间为 3 小时
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 个视频 （总计 54 分钟）, 2 个阅读材料, 4 个测验
5 个视频
Reward design15分钟
State and Action Value Functions13分钟
Measuring Policy Optimality6分钟
Policy: evaluation & improvement10分钟
Policy and value iteration8分钟
2 个阅读材料
Advanced Reward Design10分钟
Discrete Stochastic Dynamic Programming10分钟
3 个练习
Reward design8分钟
Optimality in RL10分钟
Policy Iteration14分钟
周
3完成时间为 5 小时
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 个视频 （总计 47 分钟）, 1 个阅读材料, 4 个测验
6 个视频
Monte-Carlo & Temporal Difference; Q-learning8分钟
Exploration vs Exploitation8分钟
Footnote: Monte-Carlo vs Temporal Difference2分钟
Accounting for exploration. Expected Value SARSA.11分钟
On-policy vs off-policy; Experience replay7分钟
1 个阅读材料
Extras10分钟
1 个练习
Model-free reinforcement learning10分钟
周
4完成时间为 5 小时
Approximate Value Based Methods
This week we'll learn to scale things even farther up by training agents based on neural networks.
9 个视频 （总计 104 分钟）, 3 个阅读材料, 5 个测验
9 个视频
Loss functions in value based RL11分钟
Difficulties with Approximate Methods15分钟
DQN – bird's eye view9分钟
DQN – the internals9分钟
DQN: statistical issues6分钟
Double Q-learning6分钟
More DQN tricks10分钟
Partial observability17分钟
3 个阅读材料
TD vs MC10分钟
Extras10分钟
DQN follow-ups10分钟
3 个练习
MC & TD8分钟
SARSA and QLeaning8分钟
DQN12分钟
4.1
70 个审阅33%
完成这些课程后已开始新的职业生涯
56%
通过此课程获得实实在在的工作福利
33%
加薪或升职
来自Practical Reinforcement Learning的热门评论
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.
Challenging (unlike many other courses on Coursera, it does not baby you and does not seem to be targeting as high a pass rate as possible), but very very rewarding.
讲师
Pavel Shvechikov
Researcher at HSE and Sberbank AI LabHSE Faculty of Computer Science
Alexander Panin
LecturerHSE Faculty of Computer Science
关于 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
关于 高级机器学习 专项课程
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.
常见问题
我什么时候能够访问课程视频和作业？
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。
我订阅此专项课程后会得到什么？
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。
退款政策是如何规定的？
有助学金吗？
还有其他问题吗？请访问 学生帮助中心。
