DiffuserLite: Towards Real-time Diffusion Planning

TL;DR

DiffuserLite is a lightweight diffusion planning framework that significantly increases decision-making speed while maintaining state-of-the-art performance across multiple benchmarks, enabling real-time decision-making in complex domains.

Contribution

The paper introduces DiffuserLite, a novel, fast, and lightweight diffusion planning method with a planning refinement process that enhances decision frequency and can serve as a plugin for other algorithms.

Findings

Achieves 122.2Hz decision-making frequency, 112.7x faster than existing methods.

Reaches state-of-the-art results on D4RL, Robomimic, and FinRL benchmarks.

Can be integrated as a plugin to improve other diffusion planning algorithms.

Abstract

Diffusion planning has been recognized as an effective decision-making paradigm in various domains. The capability of generating high-quality long-horizon trajectories makes it a promising research direction. However, existing diffusion planning methods suffer from low decision-making frequencies due to the expensive iterative sampling cost. To alleviate this, we introduce DiffuserLite, a super fast and lightweight diffusion planning framework, which employs a planning refinement process (PRP) to generate coarse-to-fine-grained trajectories, significantly reducing the modeling of redundant information and leading to notable increases in decision-making frequency. Our experimental results demonstrate that DiffuserLite achieves a decision-making frequency of 122.2Hz (112.7x faster than predominant frameworks) and reaches state-of-the-art performance on D4RL, Robomimic, and FinRL benchmarks. In addition, DiffuserLite can also serve as a flexible plugin to increase the decision-making frequency of other diffusion planning algorithms, providing a structural design reference for future works. More details and visualizations are available at https://diffuserlite.github.io/.