DeepCO: Offline Combinatorial Optimization Framework Utilizing Deep Learning
This work addresses offline combinatorial optimization problems, such as warehouse sequence optimization, for industries where real-time simulation is impractical, though it appears incremental as it builds on existing deep learning methods for optimization.
The authors tackled the problem of offline combinatorial optimization, which is common in industrial applications due to safety and cost constraints, by proposing DeepCO, a deep learning-based framework. They evaluated it on an offline variation of the Travelling Salesman Problem for warehouse operations, reducing route length by 5.7% on average compared to baseline methods.
Combinatorial optimization serves as an essential part in many modern industrial applications. A great number of the problems are offline setting due to safety and/or cost issues. While simulation-based approaches appear difficult to realise for complicated systems, in this research, we propose DeepCO, an offline combinatorial optimization framework utilizing deep learning. We also design an offline variation of Travelling Salesman Problem (TSP) to model warehouse operation sequence optimization problem for evaluation. With only limited historical data, novel proposed distribution regularized optimization method outperforms existing baseline method in offline TSP experiment reducing route length by 5.7% averagely and shows great potential in real world problems.