Habitizing Diffusion Planning for Efficient and Effective Decision Making
This work addresses the efficiency bottleneck for real-world applications of diffusion planning, offering a biologically-inspired solution to make these models practical.
The paper tackles the slow inference speed of diffusion planning models in decision-making by introducing Habi, a framework that accelerates them to over 800 Hz on a laptop CPU while maintaining or improving performance on D4RL benchmarks.
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.