Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning
This addresses a complex logistics optimization problem for routing and scheduling applications, representing an incremental improvement over existing methods.
The paper tackles the multiple-vehicle traveling salesman problem with time windows and customer rejections (mTSPTWR) by proposing a deep reinforcement learning framework with manager and worker agents, which outperforms baselines in solution quality and computation time and generalizes to larger unseen instances.
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections. Particularly, in the proposed framework, a manager agent learns to divide mTSPTWR into sub-routing tasks by assigning customers to each vehicle via a Graph Isomorphism Network (GIN) based policy network. A worker agent learns to solve sub-routing tasks by minimizing the cost in terms of both tour length and rejection rate for each vehicle, the maximum of which is then fed back to the manager agent to learn better assignments. Experimental results demonstrate that the proposed framework outperforms strong baselines in terms of higher solution quality and shorter computation time. More importantly, the trained agents also achieve competitive performance for solving unseen larger instances.