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 course Fundamentals of Reinforcement Learning certification course is offered by Coursera by collaboration with the University of Alberta to make the aspirants skilful with machine learning and applications of Artificial Intelligence. The course is free to enrol and can access all the course materials free of cost. Therefore aspirants can use the opportunity for growing their career with a course completion certificate and increase the chances of hiring.
With the digital connection over the world, Business Intelligence over decision making is made essential in organizations. Decision making increases the prosperity of the business. Therefore the use of decision making with Artificial Intelligence and machine learning became most popular when the programme comes into existence. Organizations are looking forward to candidates who are skilled in this type of Artificial Intelligence, Robotics, Machine learning and, the Internet of things (IoT) as well
Coursera is the digital platform to learn the concepts that are offered for free. Candidates can learn throughout their lifetime and can avail of certificates after completion of the Fundamentals of Reinforcement Learning Training course.
The Highlights
- Offered by University of Alberta
- Offered by Alberta Machine Intelligence Institute
- Approximately 15 hours to complete the course
- Certification by Coursera
- Availability in different language subtitles
Programme Offerings
- Study Materials
- Online video lectures
- quizzes
- Mobile access
- assignments
- practice assessments
- Exercises
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | University of Alberta, EdmontonCoursera |
Fundamentals of Reinforcement Learning Fee Structure :
Description | Amount |
Course Fee, 1 Month | Rs. 6,757 |
Course Fee, 3 Months | Rs. 13,514 |
Course Fee, 6 Months | Rs. 20,271 |
Eligibility Criteria
Certificate qualifying details
It is mandatory for the candidate to complete the course and submit all the assignments in the given time to get the certificate. Otherwise, no certificate will be awarded to the candidate. Also, the candidate will be given a Fundamentals of Reinforcement Learning certification by Coursera only if he/she pays the fee. Or else the candidate can learn the course without a certificate for free.
What you will learn
Once the Fundamentals of Reinforcement Learning certification syllabus is pursued by the candidates, they will learn and master different concepts that are mentioned below:
- Dynamic programming to optimize the costs and maximizing the profits in sales and marketing
- Decision processes about the techniques of deciding during risks
- Decision making to choose the best among different alternatives
Who it is for
The Fundamentals of Reinforcement Learning programme shall be ideal for those who are keen on becoming ML Engineers.
Admission Details
Application form details for Fundamentals of Reinforcement Learning classes are as follows:
Step 1: Visit the website https://www.coursera.org/learn/fundamentals-of-reinforcement-learning
and click on enrol now button
Step 2: Candidate will be asked to choose the type of course namely course with or without certification and then click continue
Step 3: the candidate will be asked to register or fill in all the relevant details and if the candidate needs a certificate he/she should pay and he is taken to the payment gateway and the fee is paid online
Step 4: Next candidate will be confirmed if he/she is eligible for financial aid or not by email.
Step 5: Thereby candidate receives a confirmation message and they can continue the course
The Syllabus
Videos
- Specialization Introduction
- Course Introduction
- Meet your instructors!
- Your Specialization Roadmap
Readings
- Reinforcement Learning Textbook
- Read Me: Pre-requisites and Learning Objectives
Discussion Prompt
- Meet and Greet!
Videos
- Sequential Decision Making with Evaluative Feedback
- Learning Action Values
- Estimating Action Values Incrementally
- What is the trade-off?
- Optimistic Initial Values
- Upper-Confidence Bound (UCB) Action Selection
- Jonathan Langford: Contextual Bandits for Real World Reinforcement Learning
- Week 1 Summary
Readings
- Module 1 Learning Objectives
- Weekly Reading
- Chapter Summary
Assignment
- Sequential Decision-Making
Programming Assignment
- Bandits and Exploration/Exploitation
Discussion Prompt
- Compare bandits to supervised learning
Plugins
- Let's play a game!
- What's underneath?
Videos
- Markov Decision Processes
- Examples of MDPs
- The Goal of Reinforcement Learning
- Michael Littman: The Reward Hypothesis
- Continuing Tasks
- Examples of Episodic and Continuing Tasks
- Week 2 Summary
Readings
- Module 2 Learning Objectives
- Weekly Reading
Quiz
- MDPs
Peer Review
- Graded Assignment: Describe Three MDPs
Discussion Prompt
- Is the reward hypothesis sufficient?
Videos
- Specifying Policies
- Value Functions
- Rich Sutton and Andy Barto: A brief History of RL
- Bellman Equation Derivation
- Why Bellman Equations?
- Optimal Policies
- Optimal Value Functions
- Using Optimal Value Functions to Get Optimal Policies
- Week 3 Summary
Readings
- Module 3 Learning Objectives
- Weekly Reading
- Chapter Summary
Assignments
- [Practice] Value Functions and Bellman Equations
- Value Functions and Bellman Equations
Discussion Prompt
- Check-in
Videos
- Policy Evaluation vs. Control
- Iterative Policy Evaluation
- Policy Improvement
- Policy Iteration
- Flexibility of the Policy Iteration Framework
- Efficiency of Dynamic Programming
- Warren Powell: Approximate Dynamic Programming for Fleet Management (Short)
- Warren Powell: Approximate Dynamic Programming for Fleet Management (Long)
- Week 4 Summary
- Congratulations!
Readings
- Module 4 Learning Objectives
- Weekly Reading
- Chapter Summary
Assignment
- Dynamic Programming
Programming Assignment
- Optimal Policies with Dynamic Programming
Discussion Prompt
- Where can you use dynamic programming?