Solution to the risk-sensitive average optimality equation in communicating Markov decision chains with finite state space: An alternative approach.
Rolando Cavazos-CadenaDaniel Hernández-HernándezPublished in: Math. Methods Oper. Res. (2003)
Keyphrases
- markov decision chains
- average cost
- finite state
- risk sensitive
- markov decision processes
- markov chain
- control policy
- optimal policy
- finite horizon
- model checking
- long run
- finite number
- optimal solution
- initial state
- infinite horizon
- total cost
- optimal control
- mathematical model
- state space
- stationary policies
- utility function
- control policies
- search space
- dynamical systems
- learning algorithm
- markov decision process
- policy iteration
- linear programming
- markov decision problems