Habitizing Diffusion Planning for Efficient and Effective Decision Making

TL;DR

This paper introduces Habi, a framework that accelerates diffusion planning models for decision-making, achieving over 800 Hz inference speed on benchmarks while maintaining high performance, inspired by brain's habitual behavior transition.

Contribution

Habi transforms slow diffusion planning models into fast, habitual decision-making models, enabling real-time applications without sacrificing accuracy.

Findings

Achieves 800+ Hz decision speed on D4RL benchmarks

Maintains or improves performance compared to original diffusion models

Provides insights into biological and engineering aspects of decision-making

Abstract

Diffusion models have shown great promise in decision-making, also known as diffusion planning. However, the slow inference speeds limit their potential for broader real-world applications. Here, we introduce Habi, a general framework that transforms powerful but slow diffusion planning models into fast decision-making models, which mimics the cognitive process in the brain that costly goal-directed behavior gradually transitions to efficient habitual behavior with repetitive practice. Even using a laptop CPU, the habitized model can achieve an average 800+ Hz decision-making frequency (faster than previous diffusion planners by orders of magnitude) on standard offline reinforcement learning benchmarks D4RL, while maintaining comparable or even higher performance compared to its corresponding diffusion planner. Our work proposes a fresh perspective of leveraging powerful diffusion models for real-world decision-making tasks. We also provide robust evaluations and analysis, offering insights from both biological and engineering perspectives for efficient and effective decision-making.