Self-Initiated Open World Learning for Autonomous AI Agents

arXiv:2110.11385v3 Announce Type: replace-cross
Abstract: As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained periodically on the initiation of human engineers using expanded training data. As the real-world is an open environment with unknowns or novelties, detecting novelties or unknowns, characterizing them, accommodating or adapting to them, gathering ground-truth …

abstract agents ai agents arxiv autonomous autonomous ai autonomous ai agents cs.ai cs.hc cs.lg engineers fully autonomous human learn practice think type world