Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Reinforcement Learning Coach

Gal Novik (Intel AI)
16:50–17:30 Wednesday, 10 October 2018
Location: Westminster Suite
Secondary topics:  Reinforcement Learning

Who is this presentation for?

  • Developers, data scientists, and reinforcement learning researchers

What you'll learn

  • Discover how Reinforcement Learning Coach can help you speed up your research or your reinforcement learning-based solution development


Reinforcement learning has enabled machines to play strategy games at above human levels and made its way into domains such as robotics and conversational experiences. While research in the field is booming, the tools for developing and testing new reinforcement learning algorithms or solutions can be boosted.

Gal Novik offers an overview of Reinforcement Learning Coach, an open source Python library that models the interaction between an agent and an environment in a modular way, making it easy for researchers to implement new reinforcement learning algorithms and for data scientists to integrate additional simulation environments modeling their business problems by leveraging its simple and clean interfaces. Coach comes with a large number of agents implementing state-of-the-art reinforcement learning algorithms along with multiple environments that simulate challenges in practical fields such as robotics, autonomous driving, games, and more. Coach collects statistics from the training process and supports advanced visualization techniques for debugging the agent being trained, saving time and effort to reach the desired goal, whether it is a new state-of-the-art algorithm or a functional solution.

Photo of Gal Novik

Gal Novik

Intel AI

Gal Novik is the head of the Intel AI Lab in Haifa, Israel, where he leads a team of research scientists and engineers developing state-of-the-art machine learning algorithms and tools for researchers and data scientists. His main focus areas are deep reinforcement learning, neural network compression, and Bayesian deep learning. Previously, Gal was the founder and CTO of a fintech startup and led multiple software development teams at Microsoft delivering client and server products.