On non-stationary policies and maximal invariant safe sets of controlled Markov chains.
Wei WuAri ArapostathisRatnesh KumarPublished in: CDC (2004)
Keyphrases
- non stationary
- markov chain
- markov processes
- steady state
- finite state
- random walk
- state space
- transition probabilities
- markov process
- markov model
- stochastic process
- monte carlo
- stationary distribution
- random fields
- optimal policy
- monte carlo method
- empirical mode decomposition
- adaptive algorithms
- sample path
- probabilistic automata
- change point detection
- confidence intervals
- markov decision process
- hidden markov models