Application of Newton's method to action selection in continuous state- and action-space reinforcement learning

Barry D. Nichols, Dimitris C. Dracopoulos

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

4 Citations (Scopus)

Abstract

An algorithm based on Newton's Method is proposed for action selection in continuous state- and action-space reinforcement learning without a policy network or discretization. The proposed method is validated on two benchmark problems: Cart-Pole and double Cart-Pole on which the proposed method achieves comparable or improved performance with less parameters to tune and in less training episodes than CACLA, which has previously been shown to outperform many other continuous state- and action-space reinforcement learning algorithms.

Original languageEnglish
Title of host publication22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings
Publisheri6doc.com publication
Pages141-146
Number of pages6
ISBN (Electronic)9782874190957
Publication statusPublished - 2014
Event22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Bruges, Belgium
Duration: 23 Apr 201425 Apr 2014

Publication series

Name22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings

Conference

Conference22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014
Country/TerritoryBelgium
CityBruges
Period23/04/1425/04/14

Fingerprint

Dive into the research topics of 'Application of Newton's method to action selection in continuous state- and action-space reinforcement learning'. Together they form a unique fingerprint.

Cite this