Presented By O'Reilly and Cloudera
December 5-6, 2016: Training
December 6–8, 2016: Tutorials & Conference
Singapore

Deep reinforcement learning on Spark

Adam Gibson (Skymind)
4:15pm–4:55pm Thursday, December 8, 2016
Chat, machine learning, and AI
Location: 321/322 Level: Intermediate
Average rating: ***..
(3.50, 2 ratings)

Prerequisite Knowledge

  • A working knowledge of machine learning
  • A basic understanding of neural networks (useful but not required)

What you'll learn

  • Understand the hardware requirements for training deep reinforcement learning algorithms
  • Gain an overview of the reinforcement learning library rl4j

Description

Deep reinforcement learning has swept the world with game playing and Google’s recent AlphaGo victory. Adam Gibson offers a brief overview of deep reinforcement learning on Spark, exploring how to run large-scale training on Spark and the implications on deep reinforcement learning targeting the doom environment. Adam explains how he built a game-playing agent using OpenCV-based frame processing doing large-scale training on Spark and outlines the requirements for training such a network.

Adam Gibson

Skymind

Adam Gibson is the CTO and cofounder of Skymind, a deep learning startup focused on enterprise solutions in banking and telco, and the coauthor of Deep Learning: A Practitioner’s Approach.