Saved in:
Bibliographic Details
Main Authors: Gao, Lei, Huang, Shihong, Wang, Shengjie, Ma, Hong, Zhang, Feng, Bao, Hengda, Chen, Qichang, Zhou, Weihua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.10057
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918158696185856
author Gao, Lei
Huang, Shihong
Wang, Shengjie
Ma, Hong
Zhang, Feng
Bao, Hengda
Chen, Qichang
Zhou, Weihua
author_facet Gao, Lei
Huang, Shihong
Wang, Shengjie
Ma, Hong
Zhang, Feng
Bao, Hengda
Chen, Qichang
Zhou, Weihua
contents The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing. Existing learning-based approaches often neglect practical stability-related constraints and exhibit limitations in generalizing across diverse bin dimensions. To address these limitations, we propose a novel deep reinforcement learning framework, One4Many-StablePacker (O4M-SP). The primary advantage of O4M-SP is its ability to handle various bin dimensions in a single training process while incorporating support and weight constraints common in practice. Our training method introduces two innovative mechanisms. First, it employs a weighted reward function that integrates loading rate and a new height difference metric for packing layouts, promoting improved bin utilization through flatter packing configurations. Second, it combines clipped policy gradient optimization with a tailored policy drifting method to mitigate policy entropy collapse, encouraging exploration at critical decision nodes during packing to avoid suboptimal solutions. Extensive experiments demonstrate that O4M-SP generalizes successfully across diverse bin dimensions and significantly outperforms baseline methods. Furthermore, O4M-SP exhibits strong practical applicability by effectively addressing packing scenarios with stability constraints.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem
Gao, Lei
Huang, Shihong
Wang, Shengjie
Ma, Hong
Zhang, Feng
Bao, Hengda
Chen, Qichang
Zhou, Weihua
Machine Learning
The three-dimensional bin packing problem (3D-BPP) is widely applied in logistics and warehousing. Existing learning-based approaches often neglect practical stability-related constraints and exhibit limitations in generalizing across diverse bin dimensions. To address these limitations, we propose a novel deep reinforcement learning framework, One4Many-StablePacker (O4M-SP). The primary advantage of O4M-SP is its ability to handle various bin dimensions in a single training process while incorporating support and weight constraints common in practice. Our training method introduces two innovative mechanisms. First, it employs a weighted reward function that integrates loading rate and a new height difference metric for packing layouts, promoting improved bin utilization through flatter packing configurations. Second, it combines clipped policy gradient optimization with a tailored policy drifting method to mitigate policy entropy collapse, encouraging exploration at critical decision nodes during packing to avoid suboptimal solutions. Extensive experiments demonstrate that O4M-SP generalizes successfully across diverse bin dimensions and significantly outperforms baseline methods. Furthermore, O4M-SP exhibits strong practical applicability by effectively addressing packing scenarios with stability constraints.
title One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem
topic Machine Learning
url https://arxiv.org/abs/2510.10057