Login / Signup
Convergence rate of moments in stochastic approximation with simultaneous perturbation gradient approximation and resetting.
László Gerencsér
Published in:
IEEE Trans. Autom. Control. (1999)
Keyphrases
</>
convergence rate
stochastic approximation
gradient method
policy iteration
monte carlo
step size
convergence speed
learning rate
numerical stability
reinforcement learning
linear combination
temporal difference learning
lp norm
neural network
particle swarm optimization