DeepAI AI Chat
Log In Sign Up

One model Packs Thousands of Items with Recurrent Conditional Query Learning

by   Dongda Li, et al.
Zhejiang University
The University of Hong Kong
Guangzhou University

Recent studies have revealed that neural combinatorial optimization (NCO) has advantages over conventional algorithms in many combinatorial optimization problems such as routing, but it is less efficient for more complicated optimization tasks such as packing which involves mutually conditioned action spaces. In this paper, we propose a Recurrent Conditional Query Learning (RCQL) method to solve both 2D and 3D packing problems. We first embed states by a recurrent encoder, and then adopt attention with conditional queries from previous actions. The conditional query mechanism fills the information gap between learning steps, which shapes the problem as a Markov decision process. Benefiting from the recurrence, a single RCQL model is capable of handling different sizes of packing problems. Experiment results show that RCQL can effectively learn strong heuristics for offline and online strip packing problems (SPPs), outperforming a wide range of baselines in space utilization ratio. RCQL reduces the average bin gap ratio by 1.83 cases and 7.84 our method also achieves 5.64 1000 items than the state of the art.


page 1

page 2

page 3

page 4


Comparing several heuristics for a packing problem

Packing problems are in general NP-hard, even for simple cases. Since no...

Solving Packing Problems with Few Small Items Using Rainbow Matchings

An important area of combinatorial optimization is the study of packing ...

Streaming Algorithms for Bin Packing and Vector Scheduling

Problems involving the efficient arrangement of simple objects, as captu...

A Multi-task Selected Learning Approach for Solving New Type 3D Bin Packing Problem

This paper studies a new type of 3D bin packing problem (BPP), in which ...

DeepCO: Offline Combinatorial Optimization Framework Utilizing Deep Learning

Combinatorial optimization serves as an essential part in many modern in...

Learning Practically Feasible Policies for Online 3D Bin Packing

We tackle the Online 3D Bin Packing Problem, a challenging yet practical...

Exact-K Recommendation via Maximal Clique Optimization

This paper targets to a novel but practical recommendation problem named...