So you wanna robot? Build yourself an SO-101 robot arm and train it? What if the robot would "imagine" its action before executing it? And then measure the execution against the expected outcome, improve the next run?

This new release is about closing the robot learning loop: policies that imagine the future before acting, reward models that tell you when your robot succeeds, a deployment CLI that turns failures into training data, and six new simulation benchmarks to measure it all.

The whole setup comes with a UI package too: LeLab