Coursera – Reinforcement Learning Specialization 2020-7

Description

Reinforcement learning, specialization courses, etc. offered by Coursera, which relates to the specialized topic of reinforcement learning offerings.

The learning reinforcement course consists of 4 courses which consists of reviewing adaptive learning systems and artificial intelligence (AI) offers. Taking full advantage of the potential of artificial intelligence requires the use of a reinforcement learning system. Solutions to reinforcement learning (RL) can use trial and error interactions, and using the comprehensive reinforcement learning solutions to solve real-world problems, pay.

With the completion of this specialist course, you can understand many principles of modern statistics and artificial intelligence. At the end of this course, you should also pass the advanced courses and prepare to apply the tools of artificial intelligence to solve real-world problems.

This course by the University of Alberta and the Institute of Learning, Artificial Intelligence, Alberta, as the center of the main artificial intelligence in the known world can be. advised. Rating given to the course by buyers 4.7 out of 5. With time spent 5 hours per week this course can be done in 5 months, etc. complete.

Cases in which the course is taught:

Create a reinforcement learning system to decide
Familiarity with reinforcement learning algorithms (Temporal – Difference learning, Monte Carlo, Sarsa, Q-learning, Policy Gradients, Dyna, etc.)
Understand how tooling responsibilities are reinforcement learning problems and how to apply the solutions
Understanding the subject that reinforcement learning can be used in machine learning will be used and how to complement deep learning and learning monitoring and supervision can not help.

Profile courses:

Publisher:: Coursera
Advanced level
Instructor: Martha White, Adam White
Number of lessons: 4 lessons
French language

This course will be the Reinforcement Learning Specialization

Fundamentals of Reinforcement Learning
Sample-based learning methods
Prediction and control with function approximation
A complete reinforcement learning system (Capstone)

Prerequisite course

Recommended that learners have at least one year of undergraduate computer science or 2-3 years of work experience in software development. Experience and comfort with programming in Python required. Must be comfortable converting algorithms and pseudocode into Python. Basic understanding of the concepts of statistics (distributions, sampling, expected values), linear algebra (vectors and matrices) and differential calculus (computation of derivatives)