Informações sobre o curso
4.3
89 classificações
28 avaliações
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!...
Globe

cursos 100% online

Comece imediatamente e aprenda em seu próprio cronograma.
Calendar

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.
Advanced Level

Nível avançado

Clock

Approx. 35 hours to complete

Sugerido: 6 weeks of study, 3-6 hours/week for base track, 6-9 with all the horrors of honors section...
Comment Dots

English

Legendas: English...
Globe

cursos 100% online

Comece imediatamente e aprenda em seu próprio cronograma.
Calendar

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.
Advanced Level

Nível avançado

Clock

Approx. 35 hours to complete

Sugerido: 6 weeks of study, 3-6 hours/week for base track, 6-9 with all the horrors of honors section...
Comment Dots

English

Legendas: English...

Programa - O que você aprenderá com este curso

Week
1
Clock
5 horas para concluir

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....
Reading
13 vídeos (Total de 84 min), 7 leituras, 3 testes
Video13 videos
Reinforcement learning vs all3min
Multi-armed bandit4min
Decision process & applications6min
Markov Decision Process5min
Crossentropy method9min
Approximate crossentropy method5min
More on approximate crossentropy method6min
Evolution strategies: core idea6min
Evolution strategies: math problems5min
Evolution strategies: log-derivative trick8min
Evolution strategies: duct tape6min
Blackbox optimization: drawbacks4min
Reading7 leituras
What you're getting into1min
Setting up course environment10min
Note: this course vs github course1min
Course teaser placeholder10min
Primers1min
About honors track1min
Extras10min
Week
2
Clock
3 horas para concluir

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....
Reading
5 vídeos (Total de 54 min), 2 leituras, 4 testes
Video5 videos
State and Action Value Functions13min
Measuring Policy Optimality6min
Policy: evaluation & improvement10min
Policy and value iteration8min
Reading2 leituras
Advanced Reward Design10min
Discrete Stochastic Dynamic Programming10min
Quiz3 exercícios práticos
Reward design8min
Optimality in RL10min
Policy Iteration14min
Week
3
Clock
5 horas para concluir

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....
Reading
6 vídeos (Total de 47 min), 1 leitura, 4 testes
Video6 videos
Monte-Carlo & Temporal Difference; Q-learning8min
Exploration vs Exploitation8min
Footnote: Monte-Carlo vs Temporal Difference2min
Accounting for exploration. Expected Value SARSA.11min
On-policy vs off-policy; Experience replay7min
Reading1 leituras
Extras10min
Quiz1 exercício prático
Model-free reinforcement learning10min
Week
4
Clock
5 horas para concluir

Approximate Value Based Methods

This week we'll learn to scale things even farther up by training agents based on neural networks....
Reading
9 vídeos (Total de 104 min), 3 leituras, 5 testes
Video9 videos
Loss functions in value based RL11min
Difficulties with Approximate Methods15min
DQN – bird's eye view9min
DQN – the internals9min
DQN: statistical issues6min
Double Q-learning6min
More DQN tricks10min
Partial observability17min
Reading3 leituras
TD vs MC10min
Extras10min
DQN follow-ups10min
Quiz3 exercícios práticos
MC & TD8min
SARSA and QLeaning8min
DQN12min
4.3

Melhores avaliações

por TCMay 17th 2018

Great course. Best course so far on reinforcement learning.

Instrutores

Pavel Shvechikov

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

Alexander Panin

Lecturer
HSE Faculty of Computer Science

Sobre National Research University Higher School of Economics

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 communications, IT, mathematics, engineering, and more. Learn more on www.hse.ru...

Sobre o Programa de cursos integrados Advanced Machine Learning

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....
Advanced Machine Learning

Perguntas Frequentes – FAQ

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.