Acerca de este Curso
60,449 vistas recientes

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Nivel intermedio

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...

Inglés (English)

Subtítulos: Inglés (English)

Habilidades que obtendrás

Artificial Intelligence (AI)Machine LearningReinforcement LearningFunction ApproximationIntelligent Systems

100 % en línea

Comienza de inmediato y aprende a tu propio ritmo.

Fechas límite flexibles

Restablece las fechas límite en función de tus horarios.

Nivel intermedio

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...

Inglés (English)

Subtítulos: Inglés (English)

Programa - Qué aprenderás en este curso

Semana
1
1 hora para completar

Welcome to the Course!

2 videos (Total 12 minutos), 2 lecturas
2 videos
Meet your instructors!8m
2 lecturas
Read Me: Pre-requisites and Learning Objectives10m
Reinforcement Learning Textbook10m
6 horas para completar

On-policy Prediction with Approximation

13 videos (Total 69 minutos), 1 lectura, 2 cuestionarios
13 videos
Generalization and Discrimination5m
Framing Value Estimation as Supervised Learning3m
The Value Error Objective4m
Introducing Gradient Descent7m
Gradient Monte for Policy Evaluation5m
State Aggregation with Monte Carlo7m
Semi-Gradient TD for Policy Evaluation3m
Comparing TD and Monte Carlo with State Aggregation4m
Doina Precup: Building Knowledge for AI Agents with Reinforcement Learning7m
The Linear TD Update3m
The True Objective for TD5m
Week 1 Summary4m
1 lectura
Weekly Reading: On-policy Prediction with Approximation40m
1 ejercicio de práctica
On-policy Prediction with Approximation30m
Semana
2
8 horas para completar

Constructing Features for Prediction

11 videos (Total 52 minutos), 1 lectura, 2 cuestionarios
11 videos
Generalization Properties of Coarse Coding5m
Tile Coding3m
Using Tile Coding in TD4m
What is a Neural Network?3m
Non-linear Approximation with Neural Networks4m
Deep Neural Networks3m
Gradient Descent for Training Neural Networks8m
Optimization Strategies for NNs4m
David Silver on Deep Learning + RL = AI?9m
Week 2 Review2m
1 lectura
Weekly Reading: On-policy Prediction with Approximation II40m
1 ejercicio de práctica
Constructing Features for Prediction28m
Semana
3
8 horas para completar

Control with Approximation

7 videos (Total 41 minutos), 1 lectura, 2 cuestionarios
7 videos
Episodic Sarsa in Mountain Car5m
Expected Sarsa with Function Approximation2m
Exploration under Function Approximation3m
Average Reward: A New Way of Formulating Control Problems10m
Satinder Singh on Intrinsic Rewards12m
Week 3 Review2m
1 lectura
Weekly Reading: On-policy Control with Approximation40m
1 ejercicio de práctica
Control with Approximation40m
Semana
4
6 horas para completar

Policy Gradient

11 videos (Total 55 minutos), 1 lectura, 2 cuestionarios
11 videos
Advantages of Policy Parameterization5m
The Objective for Learning Policies5m
The Policy Gradient Theorem5m
Estimating the Policy Gradient4m
Actor-Critic Algorithm5m
Actor-Critic with Softmax Policies3m
Demonstration with Actor-Critic6m
Gaussian Policies for Continuous Actions7m
Week 4 Summary3m
Congratulations! Course 4 Preview2m
1 lectura
Weekly Reading: Policy Gradient Methods40m
1 ejercicio de práctica
Policy Gradient Methods45m

Instructores

Avatar

Martha White

Assistant Professor
Computing Science
Avatar

Adam White

Assistant Professor
Computing Science

Acerca de Universidad 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....

Acerca de 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....

Acerca de Programa especializado Aprendizaje por refuerzo

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....
Aprendizaje por refuerzo

Preguntas Frecuentes

  • Una vez que te inscribes para obtener un Certificado, tendrás acceso a todos los videos, cuestionarios y tareas de programación (si corresponde). Las tareas calificadas por compañeros solo pueden enviarse y revisarse una vez que haya comenzado tu sesión. Si eliges explorar el curso sin comprarlo, es posible que no puedas acceder a determinadas tareas.

  • Cuando te inscribes en un curso, obtienes acceso a todos los cursos que forman parte del Programa especializado y te darán un Certificado cuando completes el trabajo. Se añadirá tu Certificado electrónico a la página Logros. Desde allí, puedes imprimir tu Certificado o añadirlo a tu perfil de LinkedIn. Si solo quieres leer y visualizar el contenido del curso, puedes auditar el curso sin costo.

¿Tienes más preguntas? Visita el Centro de Ayuda al Alumno.