Reproduce “Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jingwei Zhang, Bin Zi, Xiaoyu Ge
Attend2Pack addresses offline three-dimensional bin packing by separating selection of the next box from its orientation and placement. Attention encodes box relationships, while a frontier represents the packed arrangement. Prioritized oversampling gives additional training to poorly performing examples. On a generated 100-box task, it reports utility 0.870 ± 0.016, versus 0.844 for MM, with no evidence of real-world deployment.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.