Deep Policy Dynamic Programming for Vehicle Routing Problems.
Wouter KoolHerke van HoofJoaquim A. S. GromichoMax WellingPublished in: CPAIOR (2022)
Keyphrases
- vehicle routing problem
- dynamic programming
- optimal policy
- vehicle routing problem with time windows
- knapsack problem
- infinite horizon
- metaheuristic
- tabu search
- routing problem
- test instances
- state space
- markov decision problems
- traveling salesman problem
- benchmark problems
- waste collection
- benchmark instances
- memetic algorithm
- markov decision processes
- np hard
- multi depot
- partially observable markov decision processes
- combinatorial optimization
- guided local search
- variable neighborhood search
- greedy algorithm
- particle swarm optimization
- greedy randomized adaptive search procedure
- linear program
- neighborhood search
- genetic algorithm
- search strategies
- cost function
- special case
- integer programming
- single machine
- pick up and delivery
- optimal solution
- reinforcement learning
- neural network