Is There a Difference Between Machine Learning and Robotics?

Robotics is an extremely hard problem, but one thing that's a little bit different from standard machine learning is that system is actually interacting with the world. And so in robotic settings, one of the things that we've been looking at is seeing whether the robot can adapt to a new situation on the fly. That might mean maybe it kind of attempts the task once doesn't quite succeed, but if it fails at the task, that doesn't mean that it's done. From there, from there, it can actually re-try the task and try a new strategy on theFly.