Home | Publications | MDR+26a

Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

MCML Authors

Abstract

Behavioral cloning becomes difficult when the same observation admits several valid actions. We study this problem for action-chunking policies and show that different multimodal parameterizations fail in different ways. For latent-variable policies, posterior-prior regularization makes deployment-time sampling more reliable, but excessive regularization removes the action-conditioned information needed to distinguish demonstrated modes. Reducing this regularization can preserve mode information, but then success depends on whether the prior covers the relevant latent regions. For action-space generative policies, multimodality is constrained by the smoothness of the base-to-action transport: a map with small Lipschitz constant cannot assign substantial probability to many well-separated modes. Covering many modes therefore requires either sharp transitions in base space or off-support bridge regions in action space. Experiments on synthetic multimodal tasks and robotic simulation benchmarks support these mechanisms.

misc MDR+26a

Preprint

May. 2026

Authors

L. Mazza • M. Datres • A. Rodriguez • S. Bodenstedt • G. Kutyniok • S. Speidel

Links

arXiv

Research Area

 A2 | Mathematical Foundations

BibTeXKey: MDR+26a

#p-kutyniok
Back to Top