Action Time Sharing Policies for Ergodic Control of Markov Chains.
Amarjit BudhirajaXin LiuAdam ShwartzPublished in: SIAM J. Control. Optim. (2012)
Keyphrases
- markov chain
- stationary distribution
- markov process
- steady state
- transition probabilities
- monte carlo
- stochastic process
- finite state
- random walk
- markov model
- monte carlo method
- state space
- monte carlo simulation
- markov processes
- probabilistic automata
- optimal policy
- control policies
- transition matrix
- confidence intervals
- initial state
- optimal control
- multispectral
- query language
- average reward
- dynamic programming
- bayesian networks
- sample path
- machine learning