Reinforcement Learning & Generative Adversarial Networks

The objective of this module is to provide fundamental understanding of the concepts behind Reinforcement Learning, Generative Models and how to apply them to real world problems. This course follows the Univ.AI model of balancing between concept, theory, and implementation.

The course covers an introduction to the field of Reinforcement Learning covering the basic concepts, dynamic programming, Q-learning and Policy Graident Methods. The course will also give an overview of network building blocks, followed by an review of Generative Adversarial Networks and provide a understanding of state of the art models in the field.

5 weeks
Live Online
course fee
Next Cohort
To be decided
Classroom based

You learn with a group - your cohort. Build lifelong relationships and learn from one another.

LIVE, from the very best

We seek to recreate the learning environment of elite learning institutions, specifically - the Harvard M.S. in Data Science & AI

Intensive mentoring

Help is always on hand, always live, and more of it than anywhere else in the world

Meet your teacher

Our teachers hail from some of the world’s leading institutions and research labs in AI & Data Science.
In numbers


Contact Hours


Hrs of classes


Hrs of guided labs


faculty office hours


Group projects


Introduction to Generative Adversarial Networks
Evaluation metrics for GANs and Challenges in GANS
No items found.
Wasserstein GANs and GAN Hacks
State of the art GANs
No items found.
Introduction to Reinforcement Learning and Markov Decision Process
Bellman equation, Optimality and Recursive algorithms
Model-free learning and Q-Learning
Deep Q-Learning
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.
No items found.


Who is it for?

Learners and practitioners who have an understanding of intermediate AI concepts, including Convolutional Neural Networks and Transfer Models, and are looking to master more advanced concepts should enrol for AI-4. You are required to have a strong foundation in Statistics, Computer Science & Mathematics.


Your are expected to have a working knowledge of python, along with these three libraries:

  • Numpy
  • Pandas
  • Tensorflow.keras

All exercises in this course will be done in jupyter notebooks.

Note: Prior knowledge of high level machine learning libraries such as keras is necessary for this module

Before you begin the course, we have prepared for you a simple exercise to ensure your proficieny of the above libraries.


How it works


We have very carefully designed the coursework to give you, the student, a wholesome learning experience. We will hold two weekend sessions per week for a total of five weeks.


Before the session begins, students are expected to complete a pre-class reading assignment and attempt a quiz.

During Session

During the session, we will have live instruction interspaced with collaborative coding in small groups assisted by our teaching assistants. This will help you develop intuition for the core concepts and provide guidance on technical details.


After the session, students are expected to complete a short post-class quiz based on the principal concepts covered in class.

session structure


A lab is a TA driven 1.5 hour session that is divided into 3 major parts

Each lab begins by revisiting the quizzes and exercises done in the previous lecture session.After discussing exercises, we will have a semi-formal Q/A session.

All doubts pertaining, but not limited, to the previous session, and homeworks are welcome. The last part of the labs deals predominantly with the upcoming homeworks. It is directed towards giving a brief overview of the homework problem. We will discuss some code to help you get started.

Lab structure


At the end of this module, you will be able to efficiently work with reinforcement learning problems and build effective generative adversarial networks.

Job Skills

After successfully completing the program, you will be:

  • Able to define Generative Adversarial Networks suitable to solve the task at hand.
  • Able to understand the concept of Reinforcement learning.
  • Able to define your own agent and environment system to solve various problems.
  • Prepared to pursue advanced (graduate, doctorate) level studies in AI.
  • Qualified to seek upper-intermediate and senior level AI positions in the industry.

Student Projects

Sample class

Play video
We believe in the idea of active learning and our course is designed with the expectation of active participation from the students. Please find a demo of our course style and pedagogy.

Meet our Students & Alumni

Meet our Students & Alumni

Our early Alumni are going places

Frequently asked questions

Do I get a certificate for completing each course?
arrow down

For each course you complete successfully, you get a course completion certificate and a grade. All certificates are granted by Univ.AI, and signed by our founding faculty, who are Harvard and UCLA professors.

Do I get college credits for taking Univ.AI courses?
arrow down

No, we do not offer college credits for our courses. However, if you choose to pursue further education, based on knowledge acquired at Univ.AI, you will be able to test out of required courses at many universities around the world.

How are students graded and evaluated?
arrow down

We conduct both group and individual evaluations. Evaluations are based on your class performance (exercises and quizzes), labs, homeworks, and projects. We ask that you always participate and attempt exercises even if you get them wrong: participation counts towards your grade. 

Detailed evaluation criteria may vary from course to course, and are published prior to each course. Below is a representative grading structure:

  • Quiz & Exercises: 25%
  • Homework assignments: 35%
  • Participation: 10%
  • ~Forums: 5%
  • ~Lectures: 5%
  • Course-end Project: 20%

How do you mentor students at Univ.AI?
arrow down

The frequency of live sessions ensures that help is always on hand. 

Highly trained Teaching Assistants (TAs), serve as course mentors. RIght from the in-class exercise during professors’ lectures, to labs, office hours and discussion forums. TAs mentor each step of your learning journey - LIVE. Typically, they will be alongside you, live, with other members on a shared screen, discussing questions, helping clarify concepts and when necessary, typing in lines of code. TAs also grade your work. 

This real-time, live mentoring by TAs makes a decisive and unparalleled difference to the learning experience at Univ.AI.

How much time will I need to commit each week to do well at Univ.AI?
arrow down

Programs at Univ.AI are run one-course-at-a-time, and require about 12-15 hours of your time each week, including live classes, labs, office hours, homeworks, and projects. 

Every week, you have two classes of about 90 minutes each

Each session lasts about 90 minutes. 

If you can commit that kind of time every week to learn a new field, then we welcome you to apply for Univ.AI programs in Data Science, and AI irrespective of your stage of career.

What happens if I miss a session?
arrow down

We make session recordings available on video shortly after they are completed. Most participants tend to view the lecture video and then follow that up with a live Lab and office hours to catch-up. 

TAs often stay after labs and office hours to answer questions. There are lots of opportunities to catch up with missed sessions.

Enquire Now

First Name*
This is some text inside of a div block.
LAST Name*
This is some text inside of a div block.
This is some text inside of a div block.
phone number*
This is some text inside of a div block.
This is some text inside of a div block.
Choose the option that defines you the best*
This is some text inside of a div block.
Your workplace
This is some text inside of a div block.
Your college/university*
This is some text inside of a div block.
Programming experience*
This is some text inside of a div block.

Thank you for your interest!
You can now sign-up for counselling sessions to discuss courses, tuition options, career prospects and more. We will be happy to guide you through your Data Science journey.


Error! Something went wrong, please try again later