Optimality of Stationary Halting Policies and Finite Termination of Successive Approximations.
Ranel E. EricksonPublished in: Math. Oper. Res. (1988)
Keyphrases
- stationary policies
- markov decision processes
- average cost
- markov decision process
- state space
- linear program
- optimal policy
- finite state
- lot sizing
- dynamic programming
- sufficient conditions
- long run
- markov decision problems
- infinite horizon
- reward function
- finite number
- linear programming
- average reward
- closed form
- inventory level
- total cost
- non stationary
- optimal control
- revenue management
- reinforcement learning
- rewrite systems
- optimality criterion
- term rewriting
- machine learning
- markov chain
- management system
- case study
- genetic algorithm