Login / Signup
On Linear Stochastic Approximation: Fine-grained Polyak-Ruppert and Non-Asymptotic Concentration.
Wenlong Mou
Chris Junchi Li
Martin J. Wainwright
Peter L. Bartlett
Michael I. Jordan
Published in:
CoRR (2020)
Keyphrases
</>
fine grained
stochastic approximation
coarse grained
monte carlo
access control
tightly coupled
policy iteration
upper bound
fixed point
neural network
high level
reinforcement learning
worst case
temporal difference learning
user intent
data lineage