Average optimal switching of a Markov chain with a Borel state space.
Alexander YushkevichEvgueni GordienkoPublished in: Math. Methods Oper. Res. (2002)
Keyphrases
- markov chain
- state space
- stationary policies
- markov decision processes
- dynamic programming
- finite state
- average cost
- steady state
- monte carlo
- transition probabilities
- markov decision process
- markov process
- reinforcement learning
- monte carlo method
- stochastic process
- stationary distribution
- optimal policy
- markov model
- transition matrix
- state variables
- monte carlo simulation
- random walk
- state transition
- dynamical systems
- confidence intervals
- closed form
- particle filter
- search space
- markov chain monte carlo
- optimal control
- bayesian networks
- long run
- infinite horizon
- model selection
- gibbs sampler