Researchers used deep reinforcement learning to teach these strange robots how to moveDesigning robots is a finicky process, requiring an exhaustive amount of thought and care. It’s usually necessary to have a very clear idea of what you want your robot to do and how you want it to do it, and then you build a prototype, discover everything that’s wrong with it, build something different and better, and repeat until you run out of time and/or money.
But robots don’t necessarily have to be this complicated, as long as your expectations for what they should be able to do are correspondingly low