A korrent·our readingWhat is a korrent?

Reinforcement learning cannot be scaled for robots the way it was for language models, because every attempt spends real robot hours instead of data-centre compute.

robotics Machines that act in the world: humanoids, training data for robots, and how far behind language models they run.

reinforcement learning Training by reward: environments, verifiable tasks, value functions, and whether it works or merely beats what came before.