Average cost criterion induced by the regular utility function for continuous-time Markov decision processes.
Qingda WeiXian ChenPublished in: Discret. Event Dyn. Syst. (2017)
Keyphrases
- utility function
- average cost
- markov decision processes
- state space
- optimal control
- stationary policies
- optimal policy
- finite state
- decision makers
- decision problems
- finite horizon
- probability distribution
- dynamic programming
- policy iteration
- reinforcement learning
- approximate dynamic programming
- expected utility
- risk sensitive
- infinite horizon
- decision theory
- average reward
- markov chain
- control policy
- dynamical systems
- long run
- markov decision process
- action sets
- initial state
- partially observable
- total cost
- multistage
- markov decision problems
- linear programming
- optimality criterion
- stochastic processes
- finite number
- action space
- linear program
- least squares
- decision making
- machine learning