Excited to share what we've been working on at @OpenAI Robotics for the past year: we used RL and a new technique called automatic domain randomization to train a robot to solve Rubik's Cube. 1/n https://t.co/2POhgMLzql
— Peter Welinder (@npew) October 15, 2019
from Twitter https://twitter.com/npew
October 15, 2019 at 08:54AM
via IFTTT
No comments:
Post a Comment