Login / Signup
Improved Simultaneous Perturbation Stochastic Approximation and Its Application in Reinforcement Learning.
Xiumei Yue
Published in:
CSSE (1) (2008)
Keyphrases
</>
stochastic approximation
reinforcement learning
monte carlo
policy iteration
temporal difference learning
neural network
theoretical guarantees
machine learning
search algorithm
learning process
cost function
state space
sufficient conditions