SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring

arXiv:2404.03386v1 Announce Type: cross
Abstract: In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by domain alignment, which incurs extra computation and storage costs, and these methods fail to handle the \textit{hard cases} where the viewpoint gap is too large. To alleviate the above problems, we introduce active sensoring in the visual IL setting and …

abstract agent alignment arxiv computation costs cs.ai cs.lg cs.ro domain expert extra failure imitation learning person perspectives sensor storage storage costs type via visual world