Contractive Approximations in Risk-Sensitive Average Semi-Markov Decision Chains on a Finite State Space.
Carlos Camilo-GarayRolando Cavazos-CadenaHugo Cruz-SuárezPublished in: J. Optim. Theory Appl. (2022)
Keyphrases
- markov decision chains
- finite state
- average cost
- risk sensitive
- markov decision processes
- markov chain
- model checking
- optimal policy
- finite horizon
- long run
- optimal control
- policy iteration
- finite number
- search space
- reinforcement learning
- initial state
- steady state
- state space
- infinite horizon
- model free
- decision theoretic
- bayesian networks
- multistage
- action space
- control policies
- search algorithm