Scalable multi-product inventory control with lead time constraints using reinforcement learning.
Hardik MeisheriNazneen N. SultanaMayank BaranwalVinita BaniwalSomjit NathSatyam VermaBalaraman RavindranHarshad KhadilkarPublished in: Neural Comput. Appl. (2022)
Keyphrases
- inventory control
- lead time
- customer demand
- reinforcement learning
- supply chain
- single product
- assembly systems
- pricing strategies
- inventory models
- holding cost
- stochastic demand
- service level
- lot sizing
- inventory systems
- production planning
- finite horizon
- single item
- random variables
- customer service
- infinite horizon
- learning algorithm
- planning horizon
- lost sales
- base stock policy
- setup cost
- inventory level
- total cost
- inventory management
- optimal policy
- single stage
- markov decision process
- periodic review
- utility function
- demand distributions