Goal

1. Algorithms for Online Packing Optimization
2. build a software UI/UX

problem overview

Method

"heuristic"：启发式算法，这里指非学习型、基于规则的算法，通常用于对比强化学习（RL）模型的性能。

First Month

day1:see demo in manufacturing, try to solve bin-packing problem use RL method bin:a pallet(托盘) or container

Learning materials

Tried code

1. https://github.com/Chiba9/Irregular-Object-Packing
2. https://github.com/alexfrom0815/Online-3D-BPP-DRL
3. https://github.com/alexfrom0815/Online-3D-BPP-PCT

Bilibili

• ICLR论文视频：Learning Efficient Online 3D Bin Packing on Packing Configuration Trees
  • Online-3D-BPP-PCT
  • 论文：https://ojs.aaai.org/index.php/AAAI/article/view/16155
  • 代码：https://github.com/alexfrom0815/Online-3D-BPP-PCT
• AAAI论文视频：Online 3D Bin Packing with Constrained Deep Reinforcement Learning
  • 笔记：Online-3D-BPP-DRL
  • 代码：Online-3D-BPP-DRL github

Youtube

• Using Reinforcement Learning to Solve a Variation of the 3D Bin Packing Problem
• RL李宏毅
  • https://www.youtube.com/watch?v=XWukX-ayIrs