Reinforcement Learning for Multi-Truck Vehicle Routing Problems.
Randall CorrellSean J. WeinbergFabio SanchesTakanori IdeTakafumi SuzukiPublished in: CoRR (2022)
Keyphrases
- vehicle routing problem
- reinforcement learning
- metaheuristic
- vehicle routing problem with time windows
- tabu search
- benchmark problems
- routing problem
- traveling salesman problem
- test instances
- benchmark instances
- waste collection
- np hard
- combinatorial optimization
- memetic algorithm
- state space
- dynamic programming
- multi depot
- neighborhood search
- variable neighborhood search
- greedy randomized adaptive search procedure
- search space
- particle swarm optimization
- special case
- decision trees
- guided local search
- feasible solution