Online TD(A) for discrete-time Markov jump linear systems.

Rafael L. Beirigo Marcos Garcia Todorov André da Motta Salles Barreto

Published in: CDC (2018)

Keyphrases

linear systems
markov chain
dynamical systems
linear equations
sufficient conditions
markov processes
control theory
coefficient matrix
learning algorithm
state space
sparse linear systems
real time
function approximation
reinforcement learning
ant colony optimization