In-context learning transfers zero-shot from simulated prompts to real robots
Original titleIn-context learning also crosses the sim-to-real gap, zero-shot. Prompts can be formed entirely from simulated experience (e.g., from a s...
AISummary
Prompts built entirely from simulated experience, such as from a scripted policy, an RL agent, or a teleoperated simulated robot, can produce behaviors on a real robot. The model was not trained on the task in either the simulator or the real world, so the transfer is zero-shot.
Source: Generalist · x.comPublished · added here