A Central Limit Theorem for Temporally Nonhomogenous Markov Chains with Applications to Dynamic Programming.
Alessandro ArlottoJ. Michael SteelePublished in: Math. Oper. Res. (2016)
Keyphrases
- markov chain
- central limit theorem
- dynamic programming
- state space
- steady state
- probability distribution
- finite state
- heavy traffic
- stochastic process
- transition probabilities
- monte carlo method
- stationary distribution
- markov process
- optimal control
- markov processes
- markov model
- transition matrix
- markov decision processes
- sample path
- random walk
- confidence intervals
- optimal policy
- state dependent
- markov decision process
- initial state
- machine learning
- probabilistic automata
- hidden markov models