Reinforcement Learning-based approach for dynamic vehicle routing problem with stochastic demand.
Chenhao ZhouJingxin MaLouis DougeEk Peng ChewLoo Hay LeePublished in: Comput. Ind. Eng. (2023)
Keyphrases
- stochastic demand
- reinforcement learning
- optimal policy
- infinite horizon
- inventory control
- finite horizon
- markov decision processes
- optimal control
- markov decision process
- lead time
- lost sales
- state space
- long run
- decision problems
- single item
- dynamic programming
- learning algorithm
- machine learning
- steady state
- inventory level