Adaptive Temporal Difference Learning With Linear Function Approximation

T, Sun; H, Shen; T, Chen; D, Li

doi:10.1109/tpami.2021.3119645

Public

Adaptive Temporal Difference Learning With Linear Function Approximation.

Published in IEEE transactions on pattern analysis and machine intelligence • Nov 7, 2022

NobleIDNI4P44W09R05S60

Authors:

Sun T

,

Shen H

,

Chen T

Abstract

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD( λ) is very sensitive to the choice of stepsizes. Oftentimes, TD(0) suffers from slow convergence. Motivated by the tight link bet...

Discussions