A bounded cost condition for the existence of average optimal stationary policies of linear stochastic systems.
Alessandro N. VargasJoão B. R. do ValPublished in: ECC (2009)
Keyphrases
- stationary policies
- average cost
- stochastic systems
- markov decision processes
- sufficient conditions
- long run
- finite state
- linear program
- optimal policy
- state space
- finite number
- total cost
- markov decision process
- infinite horizon
- dynamic programming
- optimal control
- lot sizing
- linear programming
- finite horizon
- multistage
- markov decision problems
- stochastic models
- initial state
- setup cost
- holding cost
- expected cost
- decision problems
- reward function
- partially observable
- sample path
- confidence intervals