Exploring TD error as a heuristic for $\sigma$ selection in Q($\sigma$, $\lambda$)
Machine Learning
2019-12-24 v1 Machine Learning
Abstract
In the landscape of TD algorithms, the Q(, ) algorithm is an algorithm with the ability to perform a multistep backup in an online manner while also successfully unifying the concepts of sampling with using the expectation across all actions for a state. indicates the extent to which sampling is used. Selecting the value of {\sigma} can be based on characteristics of the current state rather than having a constant value or being time based. This report explores the viability of such a TD-error based scheme.
Keywords
Cite
@article{arxiv.1912.10316,
title = {Exploring TD error as a heuristic for $\sigma$ selection in Q($\sigma$, $\lambda$)},
author = {Abhishek Nan},
journal= {arXiv preprint arXiv:1912.10316},
year = {2019}
}