Discrete-time generalized policy iteration ADP algorithm with approximation errors.

Qinglai Wei Benkai Li Ruizhuo Song

Published in: SSCI (2017)

Keyphrases

dynamic programming
learning algorithm
search space
np hard
stochastic approximation
computational complexity
cost function
monte carlo
objective function
optimal solution
probabilistic model
particle swarm optimization
graph cuts
optimal policy
convergence rate
policy iteration