How to Train a Robot to Stand Up in a Virtual Reality Environment

There's been some work using a deep learning technique called reinforcement learning where they basically create a physical model of the robot. Then just give it a goal that says hey try to stand up just move around until you can stand up and then turn it loose, tens of thousands of copies of it are created. And very quickly they figure out not only how to stand up but you can teach them how to walk as well like put hundreds of them in a crowd and they can navigate an open space without crashing into anybody else.