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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publication2017 9th Computer Science and Electronic Engineering (CEEC)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages55-59
Number of pages5
ISBN (Print)978-1-5386-3008-2
DOIs
Publication statusPublished - 29 Sept 2017
Event2017 9th Computer Science and Electronic Engineering (CEEC) - Colchester, UK
Duration: 27 Sept 201729 Sept 2017

Conference

Conference2017 9th Computer Science and Electronic Engineering (CEEC)
Period27/09/1729/09/17

Keywords

  • reinforcement learning
  • eligibility trace
  • momentum
  • continuous state- and action-space
  • artificial neural networks

Fingerprint

Dive into the research topics of 'A comparison of eligibility trace and momentum on SARSA in continuous state-and action-space'. Together they form a unique fingerprint.

Cite this