Minimax Learning of Ergodic Markov Chains.

Geoffrey Wolfer Aryeh Kontorovich

Published in: CoRR (2018)

Keyphrases

markov chain
steady state
learning algorithm
finite state
stochastic process
transition matrix
markov processes
stationary distribution
transition probabilities
markov model
reinforcement learning
state space
markov process
uniformly distributed
probabilistic model
objective function
monte carlo method