Informações sobre o curso
67,991 visualizações recentes

100% on-line

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Nível intermediário

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

Aprox. 18 horas para completar

Sugerido: 4-6 hours/week...

Inglês

Legendas: Inglês

Habilidades que você terá

Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems

100% on-line

Comece imediatamente e aprenda em seu próprio cronograma.

Prazos flexíveis

Redefinir os prazos de acordo com sua programação.

Nível intermediário

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

Aprox. 18 horas para completar

Sugerido: 4-6 hours/week...

Inglês

Legendas: Inglês

Os alunos que estão fazendo este Course são

  • Data Scientists
  • Machine Learning Engineers
  • Scientists
  • Researchers
  • Financial Analysts

Programa - O que você aprenderá com este curso

Semana
1
1 horas para concluir

Welcome to the Course!

2 vídeos (Total 12 mín.), 2 leituras
2 videos
Meet your instructors!8min
2 leituras
Read Me: Pre-requisites and Learning Objectives10min
Reinforcement Learning Textbook10min
6 horas para concluir

On-policy Prediction with Approximation

13 vídeos (Total 69 mín.), 1 leitura, 2 testes
13 videos
Generalization and Discrimination5min
Framing Value Estimation as Supervised Learning3min
The Value Error Objective4min
Introducing Gradient Descent7min
Gradient Monte for Policy Evaluation5min
State Aggregation with Monte Carlo7min
Semi-Gradient TD for Policy Evaluation3min
Comparing TD and Monte Carlo with State Aggregation4min
Doina Precup: Building Knowledge for AI Agents with Reinforcement Learning7min
The Linear TD Update3min
The True Objective for TD5min
Week 1 Summary4min
1 leituras
Weekly Reading: On-policy Prediction with Approximation40min
1 exercícios práticos
On-policy Prediction with Approximation30min
Semana
2
8 horas para concluir

Constructing Features for Prediction

11 vídeos (Total 52 mín.), 1 leitura, 2 testes
11 videos
Generalization Properties of Coarse Coding5min
Tile Coding3min
Using Tile Coding in TD4min
What is a Neural Network?3min
Non-linear Approximation with Neural Networks4min
Deep Neural Networks3min
Gradient Descent for Training Neural Networks8min
Optimization Strategies for NNs4min
David Silver on Deep Learning + RL = AI?9min
Week 2 Review2min
1 leituras
Weekly Reading: On-policy Prediction with Approximation II40min
1 exercícios práticos
Constructing Features for Prediction28min
Semana
3
8 horas para concluir

Control with Approximation

7 vídeos (Total 41 mín.), 1 leitura, 2 testes
7 videos
Episodic Sarsa in Mountain Car5min
Expected Sarsa with Function Approximation2min
Exploration under Function Approximation3min
Average Reward: A New Way of Formulating Control Problems10min
Satinder Singh on Intrinsic Rewards12min
Week 3 Review2min
1 leituras
Weekly Reading: On-policy Control with Approximation40min
1 exercícios práticos
Control with Approximation40min
Semana
4
6 horas para concluir

Policy Gradient

11 vídeos (Total 55 mín.), 1 leitura, 2 testes
11 videos
Advantages of Policy Parameterization5min
The Objective for Learning Policies5min
The Policy Gradient Theorem5min
Estimating the Policy Gradient4min
Actor-Critic Algorithm5min
Actor-Critic with Softmax Policies3min
Demonstration with Actor-Critic6min
Gaussian Policies for Continuous Actions7min
Week 4 Summary3min
Congratulations! Course 4 Preview2min
1 leituras
Weekly Reading: Policy Gradient Methods40min
1 exercícios práticos
Policy Gradient Methods45min

Instrutores

Avatar

Martha White

Assistant Professor
Computing Science
Avatar

Adam White

Assistant Professor
Computing Science

Sobre Universidade de AlbertaUniversidade de Alberta

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....

Sobre 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 research institute that pushes the bounds of academic knowledge and guides business understanding of artificial intelligence and machine learning....

Sobre Programa de cursos integrados Reforço de aprendizagem

The Reinforcement Learning Specialization consists of 4 courses exploring the power of adaptive learning systems and artificial intelligence (AI). Harnessing the full potential of artificial intelligence requires adaptive learning systems. Learn how Reinforcement Learning (RL) solutions help solve real-world problems through trial-and-error interaction by implementing a complete RL solution from beginning to end. By the end of this Specialization, learners will understand the foundations of much of modern probabilistic artificial intelligence (AI) and be prepared to take more advanced courses or to apply AI tools and ideas to real-world problems. This content will focus on “small-scale” problems in order to understand the foundations of Reinforcement Learning, as taught by world-renowned experts at the University of Alberta, Faculty of Science. The tools learned in this Specialization can be applied to game development (AI), customer interaction (how a website interacts with customers), smart assistants, recommender systems, supply chain, industrial control, finance, oil & gas pipelines, industrial control systems, and more....
Reforço de aprendizagem

Perguntas Frequentes – FAQ

  • Ao se inscrever para um Certificado, você terá acesso a todos os vídeos, testes e tarefas de programação (se aplicável). Tarefas avaliadas pelos colegas apenas podem ser enviadas e avaliadas após o início da sessão. Caso escolha explorar o curso sem adquiri-lo, talvez você não consiga acessar certas tarefas.

  • Quando você se inscreve no curso, tem acesso a todos os cursos na Especialização e pode obter um certificado quando concluir o trabalho. Seu Certificado eletrônico será adicionado à sua página de Participações e você poderá imprimi-lo ou adicioná-lo ao seu perfil no LinkedIn. Se quiser apenas ler e assistir o conteúdo do curso, você poderá frequentá-lo como ouvinte sem custo.

Mais dúvidas? Visite o Central de Ajuda ao Aprendiz.