Self learning control of constrained Markov chains - a gradient approach.
Felisa J. Vázquez-AbadVikram KrishnamurthyKaterine MartinIrina BaltchevaPublished in: CDC (2002)
Keyphrases
- markov chain
- finite state
- steady state
- transition probabilities
- markov processes
- monte carlo
- markov model
- stationary distribution
- state space
- markov process
- monte carlo simulation
- random walk
- monte carlo method
- transition matrix
- stochastic process
- probabilistic automata
- confidence intervals
- optimal control
- optimal policy
- dynamic programming
- sample path
- assemble to order systems