Last Updated on
Enroll today in the new Deep Reinforcement Learning Nanodegree program!
The world of Artificial Intelligence offers a wealth of opportunity for those interested in the field, and the applications of this transformational technology are so wide-reaching that there are virtually no limits to the paths you might pursue. Udacity’s School of Artificial Intelligence offers a range of learning opportunities to support your particular interests and aspirations, and today, we are excited to officially open our new Deep Reinforcement Learning Nanodegree program for enrollment!
The arrival of this groundbreaking program is the culmination of a journey that began in March of 2016, when DeepMind’s AlphaGo stunned the world by defeating the world champion Go player Lee Sedol. As arguably the world’s most complex game, Go had long been a target for AI engineers, and this history-making victory was made possible by a branch of AI known as Deep Reinforcement Learning (DRL). In simplest form, with DRL, computers actually teach themselves through trial-and-error, by testing various approaches to learn how to perform complex tasks. Put another way, Deep Reinforcement Learning is the closest we’ve yet come to achieving Artificial General Intelligence—AI that can learn and develop like a human does!
Partnerships with Unity and the NVIDIA Deep Learning Institute
First introduced at Intersect earlier this year, and officially launched in conjunction with Unity’s Unite Berlin 2018 conference today, our new Deep Reinforcement Learning Nanodegree program is built in collaboration with Unity and the NVIDIA Deep Learning Institute. Through our collaboration with these industry-leading companies, we have built a comprehensive curriculum that is unrivaled for its both its quality and depth. Over the course of this program, you’ll implement several deep reinforcement learning algorithms using a combination of Python and deep learning libraries, to build projects that will serve as portfolio pieces to demonstrate the advanced skills you’ve acquired.
Udacity’s program instructors and content developers bring to the table a wide range of industry and academic experience. My colleagues in this program come from companies like Google, NASA, and Motorola, and hold advanced degrees from institutions such as the University of California at Berkeley, Stanford, and Georgia Tech. To add an additional layer of dynamic support as you advance through the program, we’ve also assembled an outstanding roster of talent to be our Experts-in-Residence, including:
- Arthur Juliani, Deep Learning Researcher at Unity
- Avilay Parekh, Principal Machine Learning Engineer at Unity
- Melody Guan, Machine Learning Ph.D. at Stanford University
- Peter Welinder, Research Scientist at OpenAI
- Vincent Gao, Software Engineer (Machine Learning) at Unity
As a student in this program, you’ll have the opportunity to connect directly with these experts during weekly office hours sessions.
The Deep Reinforcement Learning Nanodegree program is comprised of four courses and three projects, and to succeed in the program, you should have experience with Python, probability, machine learning, and deep learning. In the first project, entitled “Navigation,” you’ll leverage neural networks to train an agent that learns intelligent behaviors from sensory data. In the second project, “Continuous Control,” you will either train a robotic arm to reach target locations, or train a four-legged virtual creature to walk. And finally, in ”Collaboration and Competition,” you will specify a reinforcement learning task with multiple agents, and explore how to train agents in collaborative and competitive settings. You’ll do this in the context of a tennis-themed game where agents work to try and keep a ball in play for as long as possible.
If you’re in the early throes of World Cup fever, you should know that we’ve included an optional project that enables you to use what you’ve learned as a starting point for developing agents that can play soccer!
The New Frontier of AI
Deep Reinforcement Learning represents the new frontier of Artificial Intelligence, a fact made manifest by MIT’s recognition of DRL as a “Breakthrough Technology” in 2017. Despite its relative newness, DRL is already being applied in a number of important ways, many of which are highlighted in a recent article on O’Reilly, which notes applications including robotics and industrial automation; data science and machine learning; education and training; health and medicine; text, speech, and dialog systems; media and advertising; and finance.
If you’re ready to take your place at the far cutting-edge of the world’s most transformational technology, this program is for you. Deep Reinforcement Learning is one of the hottest research fields on the planet, and if your goal is to master techniques like those behind AlphaZero to build your own intelligent agents, then you’re encouraged to enroll today! The cost of the program is $999, and the classroom will open on July 10.