University of Surrey

Test tubes in the lab Research in the ATI Dance Research

An Extended Reinforcement Learning Framework to Model Cognitive Development with Enactive Pattern Representation

Xie, Zhenping and Jin, Yaochu (2018) An Extended Reinforcement Learning Framework to Model Cognitive Development with Enactive Pattern Representation IEEE Transactions on Cognitive and Developmental Systems.

[img]
Preview
Text
An Extended Reinforcement Learning Framework to Model Cognitive Development with Enactive Pattern Representation.pdf - Accepted version Manuscript

Download (679kB) | Preview

Abstract

In order to make machines more intelligent, it is inevitable to understand human-like cognitive development, in which adaptive, autonomous and progressive evolution of cognitive decision-making in interacting with the environment plays a key role. Inspired by enactive artificial intelligence and evolutionary sampling learning, anew cognitive development learning model termed evolutionary enactive learning is proposed in this work. The proposed model is constructed by extending the reinforcement learning framework and introducing the utility-selection theory to guide the coevolution of pattern representation and decision-making policies. Theoretical analysis on the model’s validity of evolutionary enactive learning is given. To further demonstrate the effectiveness of the proposed method,two simulated cognitive decision-making tasks are designed, in which pattern representation and decision-making must be jointly developed to achieve good cognitive performance. Our experimental results clearly demonstrate that the resulting learning process is rational and effective. Finally, we indicate that the proposed evolutionary enactive learning could be readily further extended by introducing existing machine learning techniques to solve more practical applications.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
NameEmailORCID
Xie, ZhenpingUNSPECIFIEDUNSPECIFIED
Jin, YaochuYaochu.Jin@surrey.ac.ukUNSPECIFIED
Date : 2018
Copyright Disclaimer : © 2018 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.
Uncontrolled Keywords : Enactive artificial intelligence; Cognitive development; Pattern representation; Evolutionary utility-selection; Cognitive decision-making
Related URLs :
Depositing User : Clive Harris
Date Deposited : 29 Jan 2018 15:55
Last Modified : 29 Jan 2018 15:55
URI: http://epubs.surrey.ac.uk/id/eprint/845707

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800