Solution to the optimality equation in a class of Markov decision chains with the average cost criterion.
Rolando Cavazos-CadenaPublished in: Kybernetika (1991)
Keyphrases
- average cost
- markov decision chains
- finite number
- markov decision processes
- long run
- finite state
- approximate dynamic programming
- control policy
- optimal policy
- optimal control
- multistage
- linear programming
- infinite horizon
- finite horizon
- inventory models
- initial state
- risk sensitive
- total cost
- linear program
- optimal solution
- mathematical model
- dynamic programming
- expected cost
- holding cost
- markov decision problems
- state space
- special case
- numerical methods
- optimality criterion
- reinforcement learning