Comparing recent assumptions for the existence of average optimal stationary policies.
Rolando Cavazos-CadenaLinn I. SennottPublished in: Oper. Res. Lett. (1992)
Keyphrases
- stationary policies
- markov decision processes
- average cost
- state space
- markov decision process
- finite state
- dynamic programming
- linear program
- action sets
- lot sizing
- sufficient conditions
- optimal policy
- infinite horizon
- linear programming
- long run
- policy iteration
- markov decision problems
- reward function
- finite number
- reinforcement learning
- optimal control
- markov chain
- initial state
- optimal solution
- machine learning
- mathematical model
- random walk
- inventory level
- decision processes
- learning algorithm