Can I read Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion on EtoBox?

Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion by Chen, Chang; Hamed, Hany; Baek, Doojin; Kang, Taegu; Bengio, Yoshua; Ahn, Sungjin is a scholarly article available to read on EtoBox.

What is Extendable Long-Horizon Planning via Hierarchical Multiscale Diffusion about?

This paper tackles a novel problem, extendable long-horizon planning-enabling agents to plan trajectories longer than those in training data without compounding errors. To tackle this, we propose the Hierarchical Multiscale Diffuser (HM-Diffuser) and Progressive Trajectory Extension (PTE), an augmentation method that iteratively generates longer trajectories by stitching shorter ones. HM-Diffuser trains on these extended trajectories using a hierarchical structure, efficiently handling tasks across multiple temporal scales. Additionally, we introduce Adaptive Plan Pondering and the Recursive HM-Diffuser, which consolidate hierarchical layers into a single model to process temporal scales recursively. Experimental results demonstrate the effectiveness of our approach, advancing diffusion-based planners for scalable long-horizon planning.

Author

Chen, Chang; Hamed, Hany; Baek, Doojin; Kang, Taegu; Bengio, Yoshua; Ahn, Sungjin

Published

2025

Language

EN