Global PAC Bounds for Learning Discrete Time Markov Chains.

Hugo Bazille Blaise Genest Cyrille Jégourel Jun Sun

Published in: CAV (2) (2020)

Keyphrases

markov chain
finite state
markov processes
learning algorithm
transition probabilities
state space
stochastic process
markov model
steady state
monte carlo method
markov process
vc dimension
monte carlo
upper bound
random walk
lower bound
objective function
reinforcement learning