English

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(σ\sigma, λ\lambda) 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. σ[0,1]\sigma \in [0, 1] 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}
}
R2 v1 2026-06-23T12:53:30.098Z