Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study | Video and Text Based |
Course Overview
The Reinforcement Learning System (Capstone) certification course is a part of the ‘Reinforcement Learning Specialisation’ programme available on Coursera. This course is the 4th and final course in the series and aims to provide the students with complete practical knowledge on how to carry out Reinforcement Learning solutions in the real world.
In the Reinforcement Learning System (Capstone) online course, students will gain well-rounded and application-based skills that will help them in implementing Reinforcement Learning. They will complete the entire Reinforcement Learning problem-solving process – starting with the formulation of a problem, assessing the appropriate algorithm for the problem, and validating the impacts of the algorithm.
The Reinforcement Learning System (Capstone) programme by Coursera is suited for anyone who is expected to perform RL solutions in their field, along with the knowledge of skills like Machine Learning and Reinforcement Learning. The candidates will delve deep into the formalisation of a problem and how to translate it into an MDP. Finally, they will submit their Parameter Study towards the end of the course.
The Highlights
- 100% online course
- Expert instructors
- Flexible deadlines
- Shareable e-certificate
- Practice quizzes
- English subtitles
- Graded feedback
- Readings
- Intermediate level course
Programme Offerings
- Financial Add
- Coursera Plus
- Flexible Deadlines
- Self-paced learning
- Graded Programming Assignments
- peer feedback
- practice quizzes
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | University of Alberta, EdmontonCoursera |
A Complete Reinforcement Learning System (Capstone) fee details:
Head | Amount |
1 Month | Rs. 6,757 |
3 Months | Rs. 13,514 |
6 Months | Rs. 20,271 |
Eligibility Criteria
This course is a part of the Reinforcement Learning Specialisation programme offered by Coursera. Thus, candidates who want to enrol for the Reinforcement Learning System (Capstone) by Coursera should have completed the first three courses in this specialisation programme.
Furthermore, you need intermediate-level knowledge of introductory linear algebra, Python 3.0 (at least one year), calculus, and probability. You should also know how to implement algorithms using pseudocode.
What you will learn
After successful completion of the Complete Reinforcement Learning System (Capstone) programme, candidates will have gained knowledge of the following:
- Skills such as Artificial Intelligence, Machine Learning and Reinforcement Learning
- How to understand a problem, create a skeleton code for it and fully translate it to MDP
- Different algorithms and how to assess the appropriateness of each one for a given problem
- How to implement your agent using Neural Network
Who it is for
The Reinforcement Learning System (Capstone) programme by Coursera is recommended for professionals who have studied computer science at the undergraduate level, for at least one year. Or else, candidates who want to pursue a career in Artificial Intelligence and Data Science.
Admission Details
To enrol for the Reinforcement Learning System (Capstone) certification course by Coursera, candidates need to follow the steps given below:
- Visit the course page. https://www.coursera.org/learn/complete-reinforcement-learning-system
- You will find the ‘Enrol for Free’ option under the course title on the page.
- Select the option and fill in your payment details. You will get a 7-day free trial, after which you can cancel the subscription before the money is deducted.
- Alternatively, you can choose the Audit option and audit the course for free.
Application Details
Candidates do not need to fill a separate application for the Reinforcement Learning System (Capstone) programme. You can simply enrol for the course by logging in to your existing Coursera account or creating a new one. After this, you have to select your preferred mode of payment and complete the fee payment for a successful application.
The Syllabus
Videos
- Course 4 Introduction
- Meet your instructors!
Readings
- Reinforcement Learning Textbook
- Pre-requisites and Learning Objectives
Discussion Prompt
- Meet and Greet
Videos
- Initial Project Meeting with Martha: Formalizing the Problem
- Andy Barto on What are Eligibility Traces and Why are they so named?
- Let's Review: Markov Decision Processes
- Let's Review: Examples of Episodic and Continuing Tasks
Programming Assignment
- MoonShot Technologies
Videos
- Meeting with Niko: Choosing the Learning Algorithm
- Let's Review: Expected Sarsa
- Let's Review: What is Q-learning?
- Let's Review: Average Reward- A New Way of Formulating Control Problems
- Let's Review: Actor-Critic Algorithm
- Csaba Szepesvari on Problem Landscape
- Andy and Rich: Advice for Students
Assignment
- Choosing the Right Algorithm
Videos
- Agent Architecture Meeting with Martha: Overview of Design Choices
- Let's Review: Non-linear Approximation with Neural Networks
- Drew Bagnell on System ID + Optimal Control
- Susan Murphy on RL in Mobile Health
Assignment
- Impact of Parameter Choices in RL
Videos
- Meeting with Adam: Getting the Agent Details Right
- Let's Review: Optimization Strategies for NNs
- Let's Review: Expected Sarsa with Function Approximation
- Let's Review: Dyna & Q-learning in a Simple Maze
- Meeting with Martha: In-depth Experience Replay
- Martin Riedmiller on The 'Collect and Infer' framework for data-efficient RL
Programming Assignment
- Implement Your Agent
Videos
- Meeting with Adam: Parameter Studies in RL
- Let's Review: Comparing TD and Monte Carlo
- Joelle Pineau about RL that Matters
- Meeting with Martha: Discussing Your Results
- Course Wrap-up
- Specialization Wrap-up
Programming Assignment
- Completing the parameter study