cs.AI, cs.LG, cs.RO, cs.SY, eess.SY

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair

arXiv:2604.04225v1 Announce Type: cross
Abstract: Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges for imitation and reinf…