On the Convergence of Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness.

Yue Huang Zhaoxian Wu Qing Ling

Published in: ICASSP (2024)

Keyphrases

fixed point
stochastic approximation
policy iteration
temporal difference learning

monte carlo
sufficient conditions
floating point
dynamical systems

belief propagation
markov decision processes
variational inequalities
fixed point theorem

supervised learning
graphical models
control strategy
finite state