Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

Deep reinforcement learning for robotics

Woj Zaremba (OpenAI)
2:35pm-3:15pm Thursday, September 6, 2018
Location: Imperial A
Secondary topics:  Reinforcement Learning

Woj Zaremba discusses deep reinforcement learning for robotics.

Photo of Woj Zaremba

Woj Zaremba

OpenAI

Wojciech Zaremba is a cofounder of OpenAI, where he leads the robotics team, which is working on developing general-purpose robots via new approaches to transfer learning and teach robots unprecedentedly complex behaviors. Previously, he spent a year at Facebook AI Research and a year at Google Brain. He holds an MS from Warsaw University/École Polytechnique and a PhD from New York University, completed under Rob Fergus and Yann LeCun. Wojciech’s research contributions include using neural network techniques to get computers to learn sophisticated algorithms from raw data—specifically, applying translation models to computer programs and building the first neural Turing machines with discrete actions. He has also worked on the discovery of adversarial examples, improved training of GANs, and the development of OpenAI gym.