The Value Iteration Algorithm in Risk-Sensitive Average Markov Decision Chains with Finite State Space.
Rolando Cavazos-CadenaRaúl Montes-de-OcaPublished in: Math. Oper. Res. (2003)
Keyphrases
- markov decision chains
- finite state
- risk sensitive
- average cost
- dynamic programming
- markov decision processes
- search space
- objective function
- computational complexity
- optimal control
- learning algorithm
- model free
- policy iteration
- optimality criterion
- optimal policy
- monte carlo
- state space
- linear programming
- markov chain
- heuristic search
- model checking
- utility function
- np hard
- optimal solution