Pith. sign in

REVIEW 4 cited by

Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.04333 v2 pith:Q722VM5G submitted 2021-07-09 cs.LG cs.AI

Jingwei Zhang , Bin Zi , Xiaoyu Ge This is my paper
classification cs.LGcs.AI
keywords learningachieveapproachattend2packdeeppackingperformancerange
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper seeks to tackle the bin packing problem (BPP) through a learning perspective. Building on self-attention-based encoding and deep reinforcement learning algorithms, we propose a new end-to-end learning model for this task of interest. By decomposing the combinatorial action space, as well as utilizing a new training technique denoted as prioritized oversampling, which is a general scheme to speed up on-policy learning, we achieve state-of-the-art performance in a range of experimental settings. Moreover, although the proposed approach attend2pack targets offline-BPP, we strip our method down to the strict online-BPP setting where it is also able to achieve state-of-the-art performance. With a set of ablation studies as well as comparisons against a range of previous works, we hope to offer as a valid baseline approach to this field of study.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. One4Many-StablePacker: An Efficient Deep Reinforcement Learning Framework for the 3D Bin Packing Problem

    cs.LG 2025-10 conditional novelty 6.0 of 10

    One deep RL model for 3D bin packing generalizes to unseen bin dimensions and enforces stability constraints, via a weighted loading-rate/height-difference reward and entropy-controlled PPO.

  2. Towards VM Rescheduling Optimization Through Deep Reinforcement Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    VMR2L, a deep reinforcement learning system, reschedules virtual machines in data centers within seconds, achieving fragment rates close to those of a slow mixed-integer programming solver.

  3. Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Operationally guided multi-anchor EMS candidates plus a 15-feature xLSTM ranker raise online industrial 3D packing density to 0.49, with 15.1% from exposure and 6.3% from learned ranking.

  4. Online 3D Bin Packing with Fast Stability Validation and Stable Rearrangement Planning

    cs.RO 2025-07 reject novelty 5.0 of 10

    A stability-validation and rearrangement framework for online 3D bin packing, using Load-Bearable Convex Polygons to mask unstable DRL actions and MCTS plus A* to plan stable unpacking and repacking.

Pith tools