Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

Deep reinforcement learning tutorial

Arthur Juliani (Unity Technologies)
1:30pm5:00pm Tuesday, June 27, 2017
Implementing AI
Location: Murray Hill E/W Level: Intermediate
Secondary topics:  Deep Learning, Machine Learning
Average rating: *****
(5.00, 2 ratings)

Prerequisite Knowledge

  • Basic knowledge of neural network methods, including convolutional networks and recurrent networks
  • Familiarity with Python and TensorFlow

Materials or downloads needed in advance

  • A laptop (The tutorial will use IPython notebooks.)
  • A GitHub account
  • GitHub repository

What you'll learn

  • Learn the differences between traditional supervised learning methods and reinforcement learning
  • Understand the basics of Q-Learning, Policy Gradient, and Actor-Critic methods for training networks to solve tasks
  • Explore how deep representation learning allows for RL methods to solve problems involving complex visual such as learning to navigate a 3D environment

Description

In the past few years, computers have been able to learn to play Atari games, Go, and first-person shooters at a superhuman level. Underlying all these accomplishments is deep reinforcement learning (RL). Unlike traditional supervised learning methods, in which networks are trained using hand-labeled data, the reinforcement learning paradigm utilizes a reward signal provided by the environment itself to train the network.

Arthur Juliani offers a deep dive into reinforcement learning, from the basics using lookup tables and GridWorld all the way to solving complex 3D tasks with deep neural networks. Along the way, Arthur introduces a variety of RL algorithms, including Q-Learning, Policy Gradient, and Actor-Critic, and shows how to extend them using deep neural networks to solve problems with much more complex and varied state and action spaces.

Photo of Arthur Juliani

Arthur Juliani

Unity Technologies

Arthur Juliani is a machine learning engineer at Unity Technologies. A researcher working at the intersection of cognitive neuroscience and deep learning, Arthur is currently working toward a PhD at the University of Oregon.