DMCA
Efficient Asymptotic Approximation in Temporal Difference Learning
by
Frédérick Garcia
,
Florent Serre
| Citations: | 1 - 1 self |
BibTeX
@MISC{Garcia_efficientasymptotic,
author = {Frédérick Garcia and Florent Serre},
title = {Efficient Asymptotic Approximation in Temporal Difference Learning},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
TD( ) is an algorithm that learns the value function associated to a policy in a Markov Decision Process (MDP). We propose in this paper an asymptotic approximation of online TD( ) with accumulating eligibility trace, called ATD( ). We then use the Ordinary Differential Equation (ODE) method to analyse ATD( ) and to optimize the choice of the parameter and the learning stepsize, and we introduce ATD, a new efficient temporal difference learning algorithm. 1
