1 code implementation • 27 Jun 2018 • Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, Sergey Levine
In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach.
no code implementations • 3 Oct 2016 • Shixiang Gu, Ethan Holly, Timothy Lillicrap, Sergey Levine
In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on off-policy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots.