Newshot

Fast Inference-Time Policy Refinement via Action-Affine World Models

Summary

arXiv:2611.15011v4 Announce Type: replace Abstract: Imitation policies can fail through compounding errors, while existing refinement methods often require additional on-policy learning or expensive online planning. Our key insight is to model the response to small corrections around a policy proposal in an affine form that enables fast optimization. We refine a frozen imitation policy using an \textit{action-affine world model} (A\textsuperscript{2}WM), trained offline from perturbed policy rollouts. Conditioned on history and the proposal, the model directly predicts a nominal trajectory and a linear action response over the full horizon. With quadratic costs and linear constraints, refinement becomes a cheap quadratic program (QP), requiring only one model evaluation and one QP solve per control step. To the best of our knowledge, we are the first to combine an action-affine world model with QP-based inference-time refinement of frozen imitation policies. Across four manipulation ta…

Original text(via arXiv cs.RO)

Computer Science > Robotics

Title:Fast Inference-Time Policy Refinement via Action-Affine World Models

Abstract:Imitation policies can fail through compounding errors, while existing refinement methods often require additional on-policy learning or expensive online planning. Our key insight is to model the response to small corrections around a policy proposal in an affine form that enables fast optimization. We refine a frozen imitation policy using an \textit{action-affine world model} (A\textsuperscript{2}WM), trained offline from perturbed policy rollouts. Conditioned on history and the proposal, the model directly predicts a nominal trajectory and a linear action response over the full horizon. With quadratic costs and linear constraints, refinement becomes a cheap quadratic program (QP), requiring only one model evaluation and one QP solve per control step. To the best of our knowledge, we are the first to combine an action-affine world model with QP-based inference-time refinement of frozen imitation policies. Across four manipulation tasks, our framework achieves the highest success rate among evaluated baselines, adding only 4.2 ms of mean refinement latency per control step, excluding base-policy sampling.
Subjects:Robotics (cs.RO)
Cite as:arXiv:2611.15011 [cs.RO]
(or arXiv:2611.15011v4 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.15011 arXiv-issued DOI via DataCite

Submission history

Access Paper:

  • HTML (experimental)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.RO
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗