Provably Efficient Gauss-Newton Temporal Difference Learning Method with Function Approximation.

Zhifa Ke Zaiwen Wen Junyu Zhang

Published in: CoRR (2023)

Keyphrases

principal components
function approximation
temporal difference learning
reinforcement learning
fixed point
temporal difference learning algorithms
model free
function approximators
gauss newton
decision trees
objective function
dynamic programming
support vector machine
text categorization
multi label