Login / Signup
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize.
Alain Durmus
Eric Moulines
Alexey Naumov
Sergey Samsonov
Kevin Scaman
Hoi-To Wai
Published in:
NeurIPS (2021)
Keyphrases
</>
stochastic approximation
step size
lower bound
upper bound
worst case
monte carlo
convergence rate
theoretical guarantees
convergence speed
approximate dynamic programming
temporal difference
probability distribution
faster convergence
np hard
policy iteration
cost function
optimal solution
reinforcement learning