Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning

12 Nov 2019  ·  Qiang Ma, Suwen Ge, Danyang He, Darshan Thaker, Iddo Drori ·

In this work, we introduce Graph Pointer Networks (GPNs) trained using reinforcement learning (RL) for tackling the traveling salesman problem (TSP). GPNs build upon Pointer Networks by introducing a graph embedding layer on the input, which captures relationships between nodes. Furthermore, to approximate solutions to constrained combinatorial optimization problems such as the TSP with time windows, we train hierarchical GPNs (HGPNs) using RL, which learns a hierarchical policy to find an optimal city permutation under constraints. Each layer of the hierarchy is designed with a separate reward function, resulting in stable training. Our results demonstrate that GPNs trained on small-scale TSP50/100 problems generalize well to larger-scale TSP500/1000 problems, with shorter tour lengths and faster computational times. We verify that for constrained TSP problems such as the TSP with time windows, the feasible solutions found via hierarchical RL training outperform previous baselines. In the spirit of reproducible research we make our data, models, and code publicly available.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Traveling Salesman Problem TSPLIB Graph Pointer Network Optimality Gap 9.35 # 2
runtime (s) 200 # 2
TSP50 Optimility Gap 5.96 # 2

Methods


No methods listed for this paper. Add relevant methods here