An optimality system for finite average Markov decision chains under risk-aversion.
Alfredo Alanís-DuránRolando Cavazos-CadenaPublished in: Kybernetika (2012)
Keyphrases
- average cost
- markov decision chains
- risk aversion
- finite number
- long run
- utility function
- markov decision processes
- risk neutral
- risk sensitive
- risk averse
- finite state
- expected utility
- exchange rate
- infinite horizon
- inventory level
- optimal control
- optimal policy
- total cost
- linear programming
- multistage
- decision makers
- linear program
- decision making
- steady state
- control policy
- average reward
- markov decision problems
- multi objective
- search space
- reinforcement learning