Deep Learning for Traveling Salesman Problems

Title Code Difficulty Recommend Prerequisites
Learning Combinatorial Optimization Algorithms over Graphs (2017) official ★☆ ★★☆ S2V, Q-learning
Learning Heuristics for the TSP by Policy Gradient (2018) none ★☆ ★★ Transformers, PG
Attention, Learn to Solve Routing Problems! (2018) official ★★★ ★★★★★ Transformer, PG
POMO: Policy Optimization with Multiple Optima for Reinforcement Learning (2020) official ★★ ★★★★ AM
Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances (2020) official ★★☆ ★★★☆ MCTS, Att-GCN
Learning Heuristics for the TSP by Policy Gradient (2021) none ★★ ★★ 2-opt, LS, AC
The Transformer Network for the Traveling Salesman Problem (2021) none Transformers, TD
Reinforcement Learning for Route Optimization with Robustness Guarantees (2021) none ★★ ★★ DQN
Combining Reinforcement Learning with SOTA algorithm called Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem (2021) official ★★ ★★☆ LKH, TD
Graph Neural Network Guided Local Search for the Traveling Salesperson Problem (2022) official ★★ ★★☆ GLS, regret algorithm
DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems (2022) official ★★ ★★★ Meta Learning
Simulation-guided Beam Search for Neural Combinatorial Optimization (2022) official ★☆ ★★★ Active Search, MCBS
Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization (2022) official ★★ POMO