Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization

arXiv:2309.08546v2 Announce Type: replace
Abstract: The pursuit of long-term autonomy mandates that robotic agents must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information. Prior-based continual learning methods are appealing for robotic applications as they are space efficient and typically do not increase in computational complexity as the number of tasks grows. Despite …

abstract adapt agents arxiv autonomy bayesian catastrophic forgetting challenge continual cs.lg environments information learn long-term moment regularization robotic robust solve tasks type