Asynchronous action-reward learning for nonstationary serial supply chain inventory control.
Chang Ouk KimIck-Hyun KwonJun-Geol BaekPublished in: Appl. Intell. (2009)
Keyphrases
- supply chain
- inventory control
- customer demand
- non stationary
- finite horizon
- supply chain management
- lead time
- reinforcement learning
- inventory management
- inventory models
- reverse logistics
- optimal policy
- decision making
- learning algorithm
- lost sales
- planning horizon
- customer service
- service level
- pricing strategies
- state space
- inventory policy