Discounted approximations in risk-sensitive average Markov cost chains with finite state space.
Rubén Blancas-RiveraRolando Cavazos-CadenaHugo Cruz-SuárezPublished in: Math. Methods Oper. Res. (2020)
Keyphrases
- average cost
- finite state
- risk sensitive
- markov chain
- markov decision processes
- markov decision chains
- optimal policy
- finite horizon
- steady state
- initial state
- infinite horizon
- markov decision problems
- model checking
- control policy
- long run
- action space
- markov decision process
- markov model
- optimal control
- reinforcement learning
- transition probabilities
- finite number
- policy iteration
- linear programming
- machine learning
- total cost
- multistage
- state space
- dynamic programming
- average reward
- search space
- decision making