将慢速扩散规划模型转化为高速习惯化决策模型，实现毫秒级响应。
Habitizing Diffusion Planning for Efficient and Effective Decision Making
- 通过模仿大脑从刻意行为到习惯化的行为转变，加速扩散规划推理。
- 在普通笔记本电脑上实现800+赫兹决策频率，远超以往扩散规划器。
- 适用于需要快速决策的实时系统，如机器人控制与自动驾驶。
扩散模型在决策任务（即扩散规划）中展现出巨大潜力，但其缓慢的推理速度限制了其在真实场景中的应用。本文提出Habi框架，将强大但缓慢的扩散规划模型转化为高效决策模型，模拟大脑中重复练习使高成本目标导向行为逐渐转变为高效习惯化行为的过程。即使在普通笔记本电脑的CPU上，该习惯化模型在标准离线强化学习基准D4RL上的平均决策频率超过800赫兹，相比以往扩散规划器提升数个数量级，同时性能相当甚至更优。本工作为利用强大扩散模型实现真实世界决策任务提供了新视角，并从生物与工程双角度进行充分评估与分析，揭示高效、有效决策的内在机制。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。