Towards high performance security policy evaluation.

Zheng Qin Fei Chen Qiang Wang Alex X. Liu Zhiguang Qin

Published in: J. Supercomput. (2012)

Keyphrases

policy evaluation
least squares
temporal difference
matrix inversion
monte carlo
reinforcement learning
markov decision processes
policy iteration
variance reduction
function approximation
model free
bayesian networks
neural network
dynamical systems
optimal policy
probabilistic model
objective function