Boston Dynamics Led a Robot Revolution. Now Its Machines Are Teaching Themselves New Tricks

“Boston Dynamics founder Marc Raibert says reinforcement learning is helping his creations gain more independence.

Reinforcement learning is a decades-old way of having a computer [learn to do something through experimentation](https://archive.is/o/0Gn2b/https://www.wired.com/story/what-alphago-teach-how-people-learn/) combined with positive or negative feedback. It came to the fore last decade when [Google DeepMind showed](https://archive.is/o/0Gn2b/https://deepmind.google/research/breakthroughs/alphago/) it could produce algorithms capable of superhuman strategy and gameplay. More recently, AI engineers have used the technique to get large language models to behave themselves.

Raibert says highly accurate new simulations have sped up what can be an arduous learning process by allowing robots to practice their moves in silico. “You don’t have to get as much physical behavior from the robot [to generate] good performance,” he says.”