Continual reinforcement learning on top of robot foundation modelsExpert
ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
NVIDIA and KAIST researchers describe in a preprint a way for a robot running a foundation model to learn a series of new assembly jobs on the factory floor without forgetting the old ones, by carrying a small reinforcement-learning add-on from task to task. On a real arm it cut the robot time needed to master each new insertion task by 31.0% to 68.5% while earlier tasks still succeeded on 19.4 of 20 trials on average.