Continuity of the optimal average cost in Markov decision chains with small risk-sensitivity.
Selene Chávez-RodríguezRolando Cavazos-CadenaHugo Cruz-SuárezPublished in: Math. Methods Oper. Res. (2015)
Keyphrases
- markov decision chains
- average cost
- risk sensitive
- optimal control
- markov decision processes
- long run
- finite number
- finite state
- optimal policy
- linear programming
- optimality criterion
- linear program
- infinite horizon
- approximate dynamic programming
- finite horizon
- multistage
- dynamic programming
- initial state
- total cost
- control policy
- state space
- holding cost
- control policies
- inventory models
- stationary policies
- reinforcement learning
- setup cost
- decision making
- control system
- machine learning
- markov decision process
- markov decision problems
- sensitivity analysis