Options
Robot Learning for Real-World Applications

When to Trust the Teacher? Adaptive Coupling in Interactive Robot Learning

Authors
  • Nikolaus Feith (CPS)
  • Elmar Rückert (CPS)

Abstract

Interactive robot learning methods typically treat the human teacher as an infallible oracle, limiting the agent's ability to surpass the expert or reject adversarial advice. We introduce MAGIC (Modulated Asymmetric Games for Interactive Control), a framework that formulates interactive learning as an asymmetric leader--follower game between a Teacher and a Learner.
The Teacher is an inverse reward field---instantiated with energy-based and flow-matching heads---that scores trajectory segments in SE(3) via contrastive learning on expert demonstrations. The Learner is a hierarchical flow-matching policy (Eye, Brain, Muscle) that maximizes a shaped reward mixing environment reward and Teacher signal. A gradient-agreement coupling determines state-dependent trust: when the Teacher's directional signal agrees with the task critic's gradient, the Teacher is trusted; otherwise it is ignored.
We prove that the alternating update satisfies the regularity conditions of two-timescale stochastic approximation.
The core pipeline is implemented and unit-tested; we present the framework, its theoretical grounding, and the planned experimental evaluation on 9 ManiSkill3 manipulation tasks, LIBERO with noisy human demonstrations, and real-robot transfer on UR3e and SO-101 arms.

How to Cite:

Feith, N. & Rückert, E., (2026) “When to Trust the Teacher? Adaptive Coupling in Interactive Robot Learning”, Proceedings of the Austrian Symposium on AI, Robotics, and Vision 3(1), 180-183.

Downloads:
Download PDF

3 Views

1 Downloads

Published on
2026-04-10

Peer Reviewed

License

Creative Commons Attribution 4.0