AI RESEARCH

Teacher-Student Representational Alignment for Reinforcement Learning-Driven Imitation Learning

arXiv CS.LG

ArXi:2605.28372v1 Announce Type: new Imitation learning (IL) from a state-based reinforcement learning (RL) policy is a common approach to overcome the curse of dimensionality in complex and high-dimensional observation spaces prevalent in robotics. This paper addresses the irreducible imitation gap that emerges when teacher and student are learned in isolation, and the teacher policy has the liberty to rely on privileged state information that the student cannot infer from its observations.