mlsanityData to 7 Oct 2026

Mitigating Dimensionality in 2D Rectangle Packing Problem under Reinforcement Learning Schema

arXiv 2409.09677 ↗First posted 15 Sep 2024cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper explores the application of Reinforcement Learning (RL) to the two-dimensional rectangular packing problem. We propose a reduced representation of the state and action spaces that allow us for high granularity. Leveraging UNet architecture and Proximal Policy Optimization (PPO), we achieved a model that is comparable to the MaxRect heuristic. However, our approach has great potential to be generalized to nonrectangular packing problems and complex constraints.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 48 references that are in the map. First posted on arXiv 15 Sep 2024.

Builds on

14 of 48 references.

References · 14

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 219
  3. 2021Deep Learning for Chest X-ray Analysis: A Surveycited by 84
  4. 2017On Pre-Trained Image Features and Synthetic Images for Deep Learningcited by 51
  5. 2020Online 3D Bin Packing with Constrained Deep Reinforcement Learningcited by 35
  6. 2019Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentationscited by 25
  7. 2018Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentationcited by 24
  8. 2021Learning Practically Feasible Policies for Online 3D Bin Packingcited by 16
  9. 2020Lung Segmentation from Chest X-rays using Variational Data Imputationcited by 15
  10. 2017Deep Convolutional Neural Networks as Generic Feature Extractorscited by 10
  11. 2022Online 3D Bin Packing Reinforcement Learning Solution with Buffercited by 8
  12. 2023MeROS: SysML-based Metamodel for ROS-based Systemscited by 6
2 more
  1. 2018A Multi-task Selected Learning Approach for Solving 3D Flexible Bin Packing Problemcited by 4
  2. 2020An intent-based approach for creating assistive robots' control systemscited by 4

Built on by

Not cited yet.