At 10-15 hrs/week
Get access to classroom immediately on enrollment
This program requires experience with Python, probability, machine learning, and deep learning.See detailed requirements.
Master the fundamentals of reinforcement learning by writing your own implementations of many classical solution methods.
Apply deep learning architectures to reinforcement learning tasks. Train your own agent that navigates a virtual world from sensory data.Navigation
Learn the theory behind evolutionary algorithms and policy-gradient methods. Design your own algorithm to train a simulated robotic arm to reach target locations.Continuous Control
Learn how to apply reinforcement learning methods to applications that involve multiple, interacting agents. These techniques are used in a variety of applications, such as the coordination of autonomous vehicles.Collaboration and Competition
from industry experts
Personal career coach and
Alexis is an applied mathematician with a Masters in Computer Science from Brown University and a Masters in Applied Mathematics from the University of Michigan. She was formerly a National Science Foundation Graduate Research Fellow.
Arpan is a computer scientist with a PhD from North Carolina State University. He teaches at Georgia Tech (within the Masters in Computer Science program), and is a coauthor of the book Practical Graph Mining with R.
Mat is a former physicist, research neuroscientist, and data scientist. He did his PhD and Postdoctoral Fellowship at the University of California, Berkeley.
Luis was formerly a Machine Learning Engineer at Google. He holds a PhD in mathematics from the University of Michigan, and a Postdoctoral Fellowship at the University of Quebec at Montreal.
Cezanne is a machine learning educator with a Masters in Electrical Engineering from Stanford University. As a former researcher in genomics and biomedical imaging, she’s applied machine learning to medical diagnostic applications.
Dana is an electrical engineer with a Masters in Computer Science from Georgia Tech. Her work experience includes software development for embedded systems in the Automotive Group at Motorola, where she was awarded a patent for an onboard operating system.
Chhavi is a Computer Science graduate student at New York University, where she researches machine learning algorithms. She is also an electronics engineer and has worked on wireless systems.
Juan is a computational physicist with a Masters in Astronomy. He is finishing his PhD in Biophysics. He previously worked at NASA developing space instruments and writing software to analyze large amounts of scientific data using machine learning techniques.
Miguel is a software engineer at Lockheed Martin. He earned a Masters in Computer Science at Georgia Tech and is an Instructional Associate for the Reinforcement Learning and Decision Making course. He’s the author of Grokking Deep Reinforcement Learning.
It is a little tough. Alexis Cook has done a great job. Her videos are detailed and slowly build the concept and code. Other instructors have added small and quick videos. Figuring out the code takes reasonable time but overall good learning. It would be good if we got a practice of creating the environment from scratch as part of a graded project in the first of 4 modules.
Overall, it has been a great opportunity for me to study re-inforcement learning through examples. The only problem I faced was watching the agent behave in the environment inside Windows, which I think was due to the nature of the gym environment which works on Linux.
yes, it's been great so far. The first project was well structured such that I could reuse much of the code from prior practice problems. This made it much more streamlined that trying to develop something from a completely blank slate.
It was amazing, the teaching quality diminishes as the videos go on, but that is expected. I would recommend a more thorough breakdown of the MARL part, since that one could be improved with one or two additional videos.
I have known some parts, but the general structure and explanations are detailed and understandable. I like the additional provided material, where I can find out about things I want to dive deeper into.
The program is well put-together! I think I learned what I wanted to in Project 1 and spent a lot less time debugging not-as-useful items than I expected. Wish I had more time to work on this!
Numbers don't lie. See what difference it makes in career searches.*
Career-seeking and job-ready graduates found a new, better job within six months of graduation.
Average salary increase for graduates who found a new, better job within six months of graduation.
The demand for engineers with reinforcement learning and deep learning skills far exceeds the number of engineers with these skills. This program offers a unique opportunity for you to develop these in-demand skills. You’ll implement several deep reinforcement learning algorithms using a combination of Python and deep learning libraries that will serve as portfolio pieces to demonstrate the skills you’ve acquired. As interest and investment in this space continues to increase, you’ll be ideally positioned to emerge as a leader in this groundbreaking field.
This program is designed to build on your existing skills in machine learning and deep learning. As such, it doesn't prepare you for a specific job, but instead expands your skills in the deep reinforcement learning domain. These skills can be applied to various applications such as gaming, robotics, recommendation systems, autonomous vehicles, financial trading, and more.
This program offers an ideal path into the world of deep reinforcement learning—a transformational technology that is reshaping our future, and driving amazing new innovations in Artificial Intelligence. If you're interested in applying AI to fields such as gaming, robotics, autonomous systems, and financial trading, this is the perfect way to get started.
No. This Nanodegree program accepts all applicants regardless of experience and specific background.
We recommend that you complete a course in Deep Learning equivalent to the Deep Learning Nanodegree program prior to entering the program. You will need to be able to communicate fluently and professionally in written and spoken English.
Additionally, you should have the following knowledge:
Basic shell scripting:
Basic statistical knowledge, including:
Intermediate differential calculus and linear algebra, including:
We have a number of Nanodegree programs and free courses that can help you prepare, including:
The Deep Reinforcement Learning Nanodegree program is comprised of content and curriculum to support three (3) projects. We estimate that students can complete the program in four (4) months working 10 hours per week.
Each project will be reviewed by the Udacity reviewer network. Feedback will be provided and if you do not pass the project, you will be asked to resubmit the project until it passes.
Please see the Udacity Executive Program FAQs for policies on enrollment in our programs.
You will need a computer running a 64-bit operating system (most modern Windows, OS X, and Linux versions will work) with at least 8GB of RAM, along with administrator account permissions sufficient to install programs including Anaconda with Python 3.6 and supporting packages. Your network should allow secure connections to remote hosts (like SSH). We will provide you with instructions to install the required software packages.