Deep Reinforcement Learning
source link: https://www.udacity.com/course/deep-reinforcement-learning-nanodegree--nd893
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
Become a Deep Reinforcement Learning Expert
Nanodegree Program
Learn the deep reinforcement learning skills that are powering amazing advances in AI. Then start applying these to applications like video games and robotics.
Estimated time
4 Months
At 10-15 hrs/week
Enroll by
April 26, 2023
Get access to classroom immediately on enrollment
Skills acquired
Value-Based Reinforcement Learning, Markov Decision Processes
What You Will Learn
Deep Reinforcement Learning
4 months to completeLearn cutting-edge deep reinforcement learning algorithms—from Deep Q-Networks (DQN) to Deep Deterministic Policy Gradients (DDPG). Apply these concepts to train agents to walk, drive, or perform other complex tasks, and build a robust portfolio of deep reinforcement learning projects.
Prerequisite knowledge
This program requires experience with Python, probability, machine learning, and deep learning.
Foundations of Reinforcement Learning
Master the fundamentals of reinforcement learning by writing your own implementations of many classical solution methods.
Value-Based Methods
Apply deep learning architectures to reinforcement learning tasks. Train your own agent that navigates a virtual world from sensory data.
Policy-Based Methods
Learn the theory behind evolutionary algorithms and policy-gradient methods. Design your own algorithm to train a simulated robotic arm to reach target locations.
Multi-Agent Reinforcement Learning
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.
All our programs include
Real-world projects from industry experts
With real-world projects and immersive content built in partnership with top-tier companies, you’ll master the tech skills companies want.
Real-time support
On demand help. Receive instant help with your learning directly in the classroom. Stay on track and get unstuck.
Career services
You’ll have access to Github portfolio review and LinkedIn profile optimization to help you advance your career and land a high-paying role.
Flexible learning program
Tailor a learning plan that fits your busy life. Learn at your own pace and reach your personal goals on the schedule that works best for you.
Program offerings
Class Content
- Content Co-created with Unity
- Real-world projects
- Project reviews
- Project feedback from experienced reviewers
Student services
- Student community
- Real-time support
Career services
- Github review
- Linkedin profile optimization
Succeed with personalized services.
We provide services customized for your needs at every step of your learning journey to ensure your success.
- Experienced Project Reviewers
- Real-Time Support
Get timely feedback on your projects.
- Personalized feedback
- Unlimited submissions and feedback loops
- Practical tips and industry best practices
- Additional suggested resources to improve
- 1,400+
project reviewers
- 2.7M
projects reviewed
- 88/100
reviewer rating
- 1.1 hours
avg project review turnaround time
Learn with the best.
Alexis Cook
Curriculum LeadAlexis 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 Chakraborty
InstructorArpan 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 Leonard
InstructorMat is a former physicist, research neuroscientist, and data scientist. He did his PhD and Postdoctoral Fellowship at the University of California, Berkeley.
Luis Serrano
InstructorLuis 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 Camacho
Curriculum LeadCezanne 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 Sheahan
Content DeveloperDana 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 Yadav
Content DeveloperChhavi 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 Delgado
Content DeveloperJuan 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 Morales
Content DeveloperMiguel 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.
Top student reviews
Antonio S.
For the moment, I'm quite happy with this Nanodegree. Just what I was expecting. That is, to fill the gap between the theory (manuals like Sutton & Barto (2018) or David Silver's lectures) and practice. Explanations are really good. The exercises as well. However, I miss a more detailed explanation of the code (line by line) in Lesson 2 "Deep Q-Networks". I'm talking about to do something similar as Mat Leonard did in "Lesson 3: Deep Learning with Pytorch" in the extracurricular module called "Neural Networks in PyTorch". This would help to understand the DQN base code (and the algorithm) much better, I think. In any case, I'm very glad because I finally have a DQN implementation that I really understand and can tweak to my liking for the research within my PhD. Overall, I'm very satisfied with the Nanodegree as well, at least for the moment. I hope to get a general, practical view/understanding of Deep RL beyond DNQ.
Taylor B.
The program is great! It is very challenging for me because I didn't have as much background in deep learning or reinforcement learning before starting. I thought the lecture material did a great job covering the key concepts and intuition, the extra material borrowed from other courses for review was key for me when it came to deep neural networks and specifically CNNs and using pytorch, and then the Sutton and Barto book added additional context and depth to the material.
The first project took me a long time because I purposefully tried to implement it without being too close to the reference implementations in exercises leading up to it thinking it would help me really drill in the material, and I think it was good for me, but to finish the nanodegree on time I may stick closer to recommended approaches in future assignments.
SENTHIL C.
Initially i was thinking am i able to get this first project complete since mostly algorithms and some advanced concepts but i made it in just 1 month itself because The way the concept explained with supportive code base and the course structure is awesome. Basically if we understand the concept right we can make it in any Language since only syntax is differ. Udacity Team made this Nano Degree in so unique way by making you understand the concept through videos , quiz and workspace to make you actual hands-on with coding ,mentor support & knowledge base . My first project I completed Udacity's workspace with additional GPU times (50 hrs), Thanks to the entire Udacity Team for your high quality , unique way of teaching and Keep en-lighting the aspirants!
Anonymous
I have got much hands-on experience through the project. The theory is easy for me and I thought it is easy to implement the algorithm. But during the coding, there are some issues and bugs. One issue the Unity environment. I am using Windows 10, there is some issue for Windows when running it on Jupyter notebook (Error: timeout of response for the environment). After going through the document of Unity, I set the environment as: env = UnityEnvironment(file_name="./Banana_Windows_x86_64/Banana.exe", no_graphics=True). Then no problem.
Ilir K.
Given the difficult situation with the COVID-19, I almost lost the ability to resume this nano degree. Thanks to Vladimir Blagojevic - my recent mentor, who kept the spirits up and also providing a complete study plan that I am following. Although I am familiar with the basics of ML & Deep Learning, I am really impressed with the materials of this program. The extracurricular materials were also very helpful. The topic was new territory for me and I am planning to invest a lot more in RL. With best regards, Ilir
Matthias v.
I am always impressed by Udacity's emphasis on "Students first". The program explains the topics very well and provides an amazing journey to gaining solid expertise. The learning curve is steep, which I personally find thrilling, and yet can be taken at your own pace/mood/schedule. The projects require quite a bit of work and really deepen the understanding further. It feels great when the task is successfully completed. Looking forward to the next steps. :-)
Deep Reinforcement Learning
Get started today
Monthly access
Pay as you go
¥ 42679
per month- Maximum flexibility to learn at your own pace.
- Cancel anytime.
4-Month access
Pay upfront and save an extra 14%
¥ 145116
¥ 170716
for 4-Month access- Save an extra 14% vs. pay as you go.
- 3 months is the average time to complete this course.
- Switch to monthly price after if more time is needed.
- Cancel anytime.
Learn
Master cutting-edge deep reinforcement learning algorithms with hands-on coding exercises, and challenging, open-ended projects.
Average Time
On average, successful students take 3 months to complete this program.
Benefits include
- Real-world projects from industry experts
- Real-time classroom support
- Career services
Program details
Program overview: Why should I take this program?
Why should I enroll?
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.
What jobs will this program prepare me for?
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.
How do I know if this program is right for me?
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.
Enrollment and admission
Do I need to apply? What are the admission criteria?
No. This Nanodegree program accepts all applicants regardless of experience and specific background.
What are the prerequisites for enrollment?
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:
- Intermediate Python programming knowledge, including:
- Strings, numbers, and variables
- Statements, operators, and expressions
- Lists, tuples, and dictionaries
- Conditions, loops
- Generators & comprehensions
- Procedures, objects, modules, and libraries
- Troubleshooting and debugging
- Research & documentation
- Problem solving
- Algorithms and data structures
Basic shell scripting:
- Run programs from a command line
- Debug error messages and feedback
- Set environment variables
- Establish remote connections
Basic statistical knowledge, including:
- Populations, samples
- Mean, median, mode
- Standard error
- Variation, standard deviations
- Normal distribution
Intermediate differential calculus and linear algebra, including:
- Derivatives & Integrals
- Series expansions
- Matrix operations through eigenvectors and eigenvalues
If I do not meet the requirements to enroll, what should I do?
Tuition and term of program
How is this Nanodegree program structured?
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.
How long is this Nanodegree program?
Access to this Nanodegree program runs for the length of time specified above. If you do not graduate within that time period, you will continue learning with month-to-month payments. See the Terms of Use and FAQs for other policies regarding the terms of access to our Nanodegree programs.
Can I switch my start date? Can I get a refund?
Please see the Udacity Program FAQs for policies on enrollment in our programs.
Software and hardware: What do I need for this program?
What software and versions will I need in this program?
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.
Jumpstart your career with Udacity.
Sign up for our newsletter to stay updated on offers and more!
By clicking "Subscribe," you agree to our Terms of Use and our Privacy Policy.
Have a question?
Ask our AI chatbot. It's in beta but ready to help!
Udacity is the trusted market leader in talent transformation. We change lives, businesses, and nations through digital upskilling, developing the edge you need to conquer what’s next.
Udacity* Nanodegree programs represent collaborations with our industry partners who help us develop our content and who hire many of our program graduates.
"Nanodegree" is a registered trademark of Udacity. © 2011–2023 Udacity, Inc.
*not an accredited university and doesn’t confer traditional degrees
© 2011–2023 Udacity, Inc.
- Legal & Privacy
- Site Map
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK