Habitizing Diffusion Planning for Efficient and Effective Decision Making

Haofei Lu, Yifei Shen, Dongsheng Li, Junliang Xing, Dongqi Han
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:40593-40613, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-lu25i, title = {Habitizing Diffusion Planning for Efficient and Effective Decision Making}, author = {Lu, Haofei and Shen, Yifei and Li, Dongsheng and Xing, Junliang and Han, Dongqi}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {40593--40613}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/lu25i/lu25i.pdf}, url = {https://proceedings.mlr.press/v267/lu25i.html}, 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.} }
Endnote
%0 Conference Paper %T Habitizing Diffusion Planning for Efficient and Effective Decision Making %A Haofei Lu %A Yifei Shen %A Dongsheng Li %A Junliang Xing %A Dongqi Han %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-lu25i %I PMLR %P 40593--40613 %U https://proceedings.mlr.press/v267/lu25i.html %V 267 %X 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.
APA
Lu, H., Shen, Y., Li, D., Xing, J. & Han, D.. (2025). Habitizing Diffusion Planning for Efficient and Effective Decision Making. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:40593-40613 Available from https://proceedings.mlr.press/v267/lu25i.html.

Related Material