Presented By O’Reilly and Intel Nervana
Put AI to work
September 17-18, 2017: Training
September 18-20, 2017: Tutorials & Conference
San Francisco, CA

Deep reinforcement learning: Recent advances and frontiers

Erran Li (Uber)
2:35pm–3:15pm Tuesday, September 19, 2017
Implementing AI
Location: Franciscan CD Level: Intermediate
Secondary topics:  Decision making, Deep learning, Robotics, Transportation and autonomous vehicles
Average rating: ***..
(3.80, 5 ratings)

Prerequisite Knowledge

  • A basic understanding of deep learning
  • Familiarity with Markov decision processes (useful but not required)

What you'll learn

  • Understand the state of the art for deep reinforcement learning, its applications, and future challenges

Description

Deep reinforcement learning has enabled artificial agents to achieve human-level performance across many challenging domains (for example, playing Atari games and Go). Li Erran Li shares several important algorithms, including deep Q-networks and asynchronous actor-critic algorithms (A3C), discusses major challenges, and explores promising results for making deep reinforcement learning applicable to real-world problems in robotics and natural language processing.

Photo of Erran Li

Erran Li

Uber

Li Erran Li is a senior research scientist in Uber’s Advanced Technologies Group and an adjunct professor in the Computer Science Department at Columbia University. His current research interests include AI, computer vision, and machine learning algorithms and systems. He is an IEEE fellow and an ACM distinguished scientist. Li holds a PhD in computer science from Cornell University, where he was advised by Joseph Halpern.