A comparison of eligibility trace and momentum on SARSA in continuous state- and action-space

Conference paper


Nichols, B. 2017. A comparison of eligibility trace and momentum on SARSA in continuous state- and action-space. 9th Computer Science & Electronic Engineering Conference (CEEC 2017). Colchester, UK 27 - 29 Sep 2017 Institute of Electrical and Electronics Engineers (IEEE). pp. 55-59 https://doi.org/10.1109/CEEC.2017.8101599
TypeConference paper
TitleA comparison of eligibility trace and momentum on SARSA in continuous state- and action-space
AuthorsNichols, B.
Abstract

Here the Newton’s Method direct action selection approach to continuous action-space reinforcement learning is extended to use an eligibility trace. This is then compared to the momentum term approach from the literature in terms of the update equations and also the success rate and number of trials required to train on two variants of the simulated Cart-Pole benchmark problem. The eligibility trace approach achieves a higher success rate with a far wider range of parameter values than the momentum approach and also trains in fewer trials on the Cart-Pole problem.

LanguageEnglish
Conference9th Computer Science & Electronic Engineering Conference (CEEC 2017)
Page range55-59
ISBN
Hardcover9781538630075
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Publication dates
Print09 Nov 2017
Publication process dates
Deposited20 Oct 2017
Accepted25 Aug 2017
Output statusPublished
Accepted author manuscript
Copyright Statement

© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

Digital Object Identifier (DOI)https://doi.org/10.1109/CEEC.2017.8101599
Book title2017 9th Computer Science and Electronic Engineering (CEEC)
Permalink -

https://repository.mdx.ac.uk/item/873qy

Download files


Accepted author manuscript
  • 8
    total views
  • 8
    total downloads
  • 1
    views this month
  • 2
    downloads this month

Export as