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

Nichols, Barry D. ORCID logoORCID: https://orcid.org/0000-0002-6760-6037 (2017) A comparison of eligibility trace and momentum on SARSA in continuous state- and action-space. 2017 9th Computer Science and Electronic Engineering (CEEC). In: 9th Computer Science & Electronic Engineering Conference (CEEC 2017), 27-29 Sep 2017, Colchester, UK. ISBN 9781538630075. [Conference or Workshop Item] (doi:10.1109/CEEC.2017.8101599)

PDF - Final accepted version (with author's formatting)
Download (434kB) | Preview


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.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 22717
Notes on copyright: © 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.”
Useful Links:
Depositing User: Barry Nichols
Date Deposited: 20 Oct 2017 11:41
Last Modified: 29 Nov 2022 20:27
URI: https://eprints.mdx.ac.uk/id/eprint/22717

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.