Tags

keep hungry keep foolish
论文阅读

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

AAAI2021 分支热图预测 + MCTS


A linearithmic heuristic for the travelling salesman problem

EJOR2021 分治求解TSP


Unsupervised Learning Permutations for TSP using Gumbel-Sinkhorn Operator

NIPS23 学习置换 + 不同分布的泛化 + 理论解释


Unsupervised Learning for Solving the Travelling Salesman Problem

NIPS23 SAG(GNN) + 带有local search的树搜索


Neural Combinatorial Optimization with Heavy Decoder-Toward Large Scale Generalization

NIPS23 重解码轻编码 + 迭代重构局部解改进


Let the Flows Tell Solving Graph Combinatorial Problems with GFlowNets

NIPS23 GFlowNets


Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

NIPS23 k-opt learn to imporve + mask优化不可行探索 + 双流解码器


DeepACO Neural-enhanced Ant Systems for Combinatorial Optimization

NIPS23 神经蚁群系统 构造+局部搜索 泛用的元启发式


Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift

NIPS23 集成学习提高泛化性


Deep Reinforcement Learning for the Electric Vehicle Routing Problem With Time Windows

EVRPTW


Combinatorial Optimization with Policy Adaptation using Latent Space Search

NIPS23 潜在空间采样学习+推理时候搜索


Winner Takes It All-Training Performant RL Populations for Combinatorial Optimization

NIPS23 多智能体(种群)学习


BQ-NCO Bisimulation Quotienting for Efficient Neural Combinatorial Optimization

NIPS23 新的马尔可夫决策过程表示并改进学习框架


组合优化

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

AAAI2021 分支热图预测 + MCTS


A linearithmic heuristic for the travelling salesman problem

EJOR2021 分治求解TSP


Unsupervised Learning Permutations for TSP using Gumbel-Sinkhorn Operator

NIPS23 学习置换 + 不同分布的泛化 + 理论解释


Unsupervised Learning for Solving the Travelling Salesman Problem

NIPS23 SAG(GNN) + 带有local search的树搜索


Neural Combinatorial Optimization with Heavy Decoder-Toward Large Scale Generalization

NIPS23 重解码轻编码 + 迭代重构局部解改进


Let the Flows Tell Solving Graph Combinatorial Problems with GFlowNets

NIPS23 GFlowNets


双层规划问题

综述和一些应用


Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

NIPS23 k-opt learn to imporve + mask优化不可行探索 + 双流解码器


DeepACO Neural-enhanced Ant Systems for Combinatorial Optimization

NIPS23 神经蚁群系统 构造+局部搜索 泛用的元启发式


Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift

NIPS23 集成学习提高泛化性


Deep Reinforcement Learning for the Electric Vehicle Routing Problem With Time Windows

EVRPTW


Combinatorial Optimization with Policy Adaptation using Latent Space Search

NIPS23 潜在空间采样学习+推理时候搜索


Winner Takes It All-Training Performant RL Populations for Combinatorial Optimization

NIPS23 多智能体(种群)学习


BQ-NCO Bisimulation Quotienting for Efficient Neural Combinatorial Optimization

NIPS23 新的马尔可夫决策过程表示并改进学习框架