Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation.

Yue Wang Shaofeng Zou Yi Zhou

Published in: NeurIPS (2021)

Keyphrases

function approximation
asymptotic analysis
reinforcement learning
learning tasks
special case
temporal difference
temporal difference learning algorithms
radial basis function
model free
function approximators
objective function
learning experience