The online 3D bin packing problem is important in logistics, warehousing and intelligent manufacturing, with solutions shifting to deep reinforcement learning (DRL) which faces challenges like low sample efficiency. This paper proposes a diffusion reinforcement learning-based algorithm, using a Markov decision chain for packing modeling, height map-based state representation and a diffusion model-based actor network. Experiments show it significantly improves the average number of packed items compared to state-of-the-art DRL methods, with excellent application potential in complex online scenarios.
@article{arxiv.2604.10953,
title = {Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy Optimization},
author = {Jie Han and Tong Li and Qingyang Xu and Yong Song and Bao Pang and Xianfeng Yuan},
journal= {arXiv preprint arXiv:2604.10953},
year = {2026}
}
Comments
8 pages, double-column. Jie Han and Tong Li contributed equally to this work. Qingyang Xu is the corresponding author