Naive Asymptotics for Hitting Time Bounds in Markov Chains.
Vernon RegoPublished in: Acta Informatica (1992)
Keyphrases
- markov chain
- steady state
- finite state
- monte carlo
- markov process
- transition probabilities
- stationary distribution
- random walk
- monte carlo method
- upper bound
- state space
- importance sampling
- monte carlo simulation
- large deviations
- stochastic process
- markov model
- confidence intervals
- markov processes
- transition matrix
- multispectral
- reinforcement learning
- asymptotically optimal
- higher order
- worst case
- generalization bounds
- variance reduction
- search space
- machine learning