Deep Policy Dynamic Programming for Vehicle Routing Problems.
Wouter KoolHerke van HoofJoaquim A. S. GromichoMax WellingPublished in: CoRR (2021)
Keyphrases
- vehicle routing problem
- dynamic programming
- optimal policy
- vehicle routing problem with time windows
- knapsack problem
- metaheuristic
- infinite horizon
- tabu search
- routing problem
- test instances
- waste collection
- traveling salesman problem
- benchmark problems
- markov decision problems
- state space
- particle swarm optimization
- multi depot
- partially observable markov decision processes
- variable neighborhood search
- combinatorial optimization
- neighborhood search
- np hard
- benchmark instances
- markov decision processes
- memetic algorithm
- reinforcement learning
- greedy randomized adaptive search procedure
- pick up and delivery
- greedy algorithm
- linear program
- ant colony optimization
- linear programming
- scheduling problem
- neural network
- single machine
- naive bayes
- simulated annealing
- optimal solution