English

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

Machine Learning 2024-09-25 v1 Optimization and Control

Abstract

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.

Keywords

Cite

@article{arxiv.2409.09677,
  title  = {Mitigating Dimensionality in 2D Rectangle Packing Problem under Reinforcement Learning Schema},
  author = {Waldemar Kołodziejczyk and Mariusz Kaleta},
  journal= {arXiv preprint arXiv:2409.09677},
  year   = {2024}
}

Comments

5th Polish Conference on Artificial Intelligence

R2 v1 2026-06-28T18:45:06.719Z