Convergence Rates for Stochastic Approximation on a Boundary.

Kody J. H. Law Neil S. Walton Shangda Yang

Published in: CoRR (2022)

Keyphrases

stochastic approximation
convergence rate
policy iteration
monte carlo
convergence speed
step size
learning rate
primal dual
temporal difference learning
reinforcement learning
gaussian kernels
artificial neural networks
markov chain
markov decision processes
function approximation
average reward