Constrained optimality for finite horizon semi-Markov decision processes in Polish spaces.
Yonghui HuangZhongfei LiXianping GuoPublished in: Oper. Res. Lett. (2014)
Keyphrases
- finite horizon
- semi markov decision processes
- average reward
- optimal policy
- markov decision processes
- average cost
- infinite horizon
- optimal stopping
- long run
- finite state
- inventory control
- decision problems
- reinforcement learning
- single product
- inventory models
- state space
- dynamic programming
- policy iteration
- multistage
- markov decision process
- sufficient conditions
- lost sales
- yield management
- initial state
- partially observable
- lot size
- lower bound
- reward function
- non stationary
- expected reward
- optimal solution
- machine learning