Growth rates and average optimality in risk-sensitive Markov decision chains.
Karel SladkýPublished in: Kybernetika (2008)
Keyphrases
- markov decision chains
- average cost
- risk sensitive
- markov decision processes
- long run
- finite state
- optimal control
- finite number
- optimal policy
- linear programming
- infinite horizon
- finite horizon
- multistage
- linear program
- optimality criterion
- state space
- total cost
- reinforcement learning
- markov decision process
- control policy
- dynamic programming
- markov chain
- policy iteration
- optimal solution
- markov decision problems
- average reward
- mathematical model
- utility function