RP-DQN: An Application of Q-Learning to Vehicle Routing Problems.
Ahmad BdeirSimon BoederTim DerneddeKirill TkachukJonas K. FalknerLars Schmidt-ThiemePublished in: KI (2021)
Keyphrases
- vehicle routing problem
- reinforcement learning
- vehicle routing problem with time windows
- metaheuristic
- state space
- benchmark problems
- test instances
- routing problem
- waste collection
- tabu search
- learning algorithm
- combinatorial optimization
- multi depot
- traveling salesman problem
- memetic algorithm
- benchmark instances
- optimal policy
- particle swarm optimization
- travel time
- variable neighborhood search
- np hard
- guided local search
- greedy randomized adaptive search procedure
- ant colony optimization
- optimization problems
- constraint satisfaction
- scatter search
- dynamic programming
- multi objective
- search space
- information retrieval
- neural network