Unsupervised Learning of Effective Actions in Robotics

arXiv:2404.02728v1 Announce Type: cross
Abstract: Learning actions that are relevant to decision-making and can be executed effectively is a key problem in autonomous robotics. Current state-of-the-art action representations in robotics lack proper effect-driven learning of the robot's actions. Although successful in solving manipulation tasks, deep learning methods also lack this ability, in addition to their high cost in terms of memory or training data. In this paper, we propose an unsupervised algorithm to discretize a continuous motion space and generate …

abstract art arxiv autonomous cs.ai cs.lg cs.ro current decision deep learning key making manipulation robot robotics state tasks type unsupervised unsupervised learning