Optimal policies for inventory systems with finite capacity and partially observed Markov-modulated demand and supply processes.
Kenan ArifogluSüleyman ÖzekiciPublished in: Eur. J. Oper. Res. (2010)
Keyphrases
- optimal policy
- partially observed
- inventory systems
- base stock policy
- lost sales
- single product
- periodic review
- finite horizon
- single stage
- lead time
- state space
- inventory models
- infinite horizon
- multistage
- markov decision processes
- dynamic programming
- inventory control
- decision problems
- reinforcement learning
- multi item
- finite state
- state dependent
- long run
- order quantity
- stochastic demand
- inventory level
- sufficient conditions
- single item
- average cost
- initial state
- markov decision process
- lot sizing
- asymptotically optimal
- total cost
- machine learning