PolicyTrim / README.md
nielsr's picture
nielsr HF Staff
Add model card and robotics pipeline tag
70b3d5d verified
|
Raw
History Blame
2.02 kB
metadata
license: apache-2.0
pipeline_tag: robotics

PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

This repository contains the models and codebase for PolicyTrim, a reinforcement learning-based post-training framework that extends the reliable action chunk length and reduces redundant physical steps for Vision-Language-Action (VLA) models.

Introduction

PolicyTrim is a two-stage RL post-training framework designed to reduce the number of inference calls required to complete robotic manipulation tasks. It targets two key factors:

  1. Reliable action chunk extension: Progressively probes longer execution windows and rewards successful rollouts that sustain longer reliable chunks.
  2. Redundancy-aware step reduction: Encourages successful trajectories that reach the goal in fewer physical steps while discouraging fragile, non-reproducible shortcuts.

Across three benchmarks (including LIBERO and ManiSkill) and three VLA models (OpenPI, OpenVLA-OFT, and GR00T), PolicyTrim improves action chunk utilization by , reduces physical execution steps by 51.4%, and achieves up to a 5.83× end-to-end deployment speedup without sacrificing task success rates.

Citation

If you find PolicyTrim helpful, please cite the following work:

@inproceedings{policytrim2026,
  title     = {PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models},
  author    = {Xianghui Wang and Feng Chen and Wenbo Zhang and Hua Yan and Zixuan Wang and Changsheng Li and Yinjie Lei},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}