A Deep Reinforcement Learning Based Real-Time Solution Policy for the Traveling Salesman Problem.
Zhengxuan LingYu ZhangXi ChenPublished in: IEEE Trans. Intell. Transp. Syst. (2023)
Keyphrases
- traveling salesman problem
- reinforcement learning
- discrete optimization problems
- combinatorial optimization
- ant colony optimization
- neighborhood search
- optimal policy
- combinatorial optimization problems
- control policy
- combinatorial problems
- optimization problems
- hamiltonian cycle
- ant colony optimization algorithm
- vehicle routing problem
- function approximation
- metaheuristic
- valid inequalities
- discrete particle swarm optimization
- crossover operator
- dynamic programming
- traveling salesman
- partially observable
- markov decision process
- model free
- discrete optimization
- simulated annealing
- search space
- policy search
- neural network
- optimal solution
- genetic local search