You can deploy this model and start earning money today!

Timsty/
pi_base_models_torch

reinforcement-learning

Views

No views yet

This repository provided the torch-version openpi checkpoints (pi0base, pi0.5base) coverted from JAX-version!

Mixture of Horizons in Action Chunking

Vision-language-action (VLA) models for robotic manipulation are highly sensitive to the chosen action chunk length, termed horizon in this work. A fixed horizon presents an inherent trade-off: longer horizons offer superior global foresight but compromise fine-grained accuracy, while shorter ones provide precise local control but struggle with long-term tasks.

To address this challenge, we propose Mixture of Horizons (MoH), a novel, plug-and-play strategy that fuses multiple horizons within a single policy. MoH processes action chunks in parallel segments with different horizons and integrates their outputs. This approach simultaneously leverages long-term foresight and short-term precision with minimal overhead, and enables Dynamic Inference through cross-horizon consensus for enhanced efficiency and robustness in complex robotic tasks.

📄 Paper
📝 Project Page
💻 Code

Introduction

Trade-off Effect	Mixture of Horizons
Figure 1: Trade-off between long-term foresight and short-term precision induced by single horizon	Figure 2: Overview of the proposed mixture-of-horizons strategy

Mitigates Trade-off: Addresses the inherent trade-off between long-term foresight and short-term precision induced by single action chunk horizons.
Plug-and-Play: Easily integrates into existing full-attention action modules with minimal training or inference overhead.
Dynamic Inference: Achieves higher efficiency and robustness by selecting stable actions through cross-horizon consensus.

More results on LIBERO

Usage

For detailed instructions on environment setup, training, and evaluation, please refer to the GitHub repository.

❤️ Acknowledgment

We express our gratitude to OpenPi, LIBERO, and RoboTwin for their open-source contributions.

📝 Citation

If you feel that this paper, models, or codes are helpful, please cite our paper, thanks for your support!

bibtex

@article{jing2025mixture_of_horizons,
  title={Mixture of Horizons in Action Chunking},
  author={Jing, Dong and Wang, Gang and Liu, Jiaqi and Tang, Weiliang and Sun, Zelong and Yao, Yunchao and Wei, Zhenyu and Liu, Yunhui and Lu, Zhiwu and Ding, Mingyu},
  journal={arXiv preprint arXiv:2511.19433},
  year={2025}
}

Timsty/pi_base_models_torch