Minimax Learning of Ergodic Markov Chains.

Geoffrey Wolfer Aryeh Kontorovich

Published in: ALT (2019)

Keyphrases

markov chain
markov process
learning algorithm
steady state
finite state
reinforcement learning
random walk
stationary distribution
objective function
dynamic programming
graphical models
monte carlo
monte carlo simulation
transition probabilities
stochastic process
probabilistic automata