Variable Socket Position Using Deep Reinforcement Learning
"A Practical Approach to Insertion with Variable Socket Position Using Deep Reinforcement Learning," by Mel Vecerik, Oleg Sushkov, David Barker, Thomas Rothorl, Todd Hester, and Jon Scholz from DeepMind, London, U.K.
Presented at the 2019 International Conference on Robotics and Automation (ICRA), Montreal, Canada.