Accelerated stochastic approximation with state-dependent noise.

Sasila Ilandarideva Anatoli B. Juditsky Guanghui Lan Tianjiao Li

Published in: CoRR (2023)

Keyphrases

state dependent
stochastic approximation
optimal policy
steady state
monte carlo
policy iteration
queueing networks
markov chain
arrival rate
stationary distribution
asymptotically optimal
queue length
single server
cost function
higher order
temporal difference learning
probabilistic model