Header

UZH-Logo

Maintenance Infos

Learning the condition of satisfaction of an elementary behavior in dynamic field theory


Luciw, M; Kazerounian, S; Lahkman, K; Richter, M; Sandamirskaya, Y (2015). Learning the condition of satisfaction of an elementary behavior in dynamic field theory. Paladyn, 6(1):180-190.

Abstract

In order to proceed along an action sequence, an autonomous agent has to recognize that the intended final condition of the previous action has been achieved. In previous work, we have shown how a sequence of actions can be generated by an embodied agent using a neural-dynamic architecture for behavioral organization, in which each action has an intention and condition of satisfaction. These components are represented by dynamic neural fields, and are coupled to motors and sensors of the robotic agent.Here,we demonstratehowthemappings between intended actions and their resulting conditions may be learned, rather than pre-wired.We use reward-gated associative learning, in which, over many instances of externally validated goal achievement, the conditions that are expected to result with goal achievement are learned. After learning, the external reward is not needed to recognize that the expected outcome has been achieved. This method was implemented, using dynamic neural fields, and tested on a real-world E-Puck mobile robot and a simulated NAO humanoid robot.

Abstract

In order to proceed along an action sequence, an autonomous agent has to recognize that the intended final condition of the previous action has been achieved. In previous work, we have shown how a sequence of actions can be generated by an embodied agent using a neural-dynamic architecture for behavioral organization, in which each action has an intention and condition of satisfaction. These components are represented by dynamic neural fields, and are coupled to motors and sensors of the robotic agent.Here,we demonstratehowthemappings between intended actions and their resulting conditions may be learned, rather than pre-wired.We use reward-gated associative learning, in which, over many instances of externally validated goal achievement, the conditions that are expected to result with goal achievement are learned. After learning, the external reward is not needed to recognize that the expected outcome has been achieved. This method was implemented, using dynamic neural fields, and tested on a real-world E-Puck mobile robot and a simulated NAO humanoid robot.

Statistics

Altmetrics

Downloads

20 downloads since deposited on 22 Feb 2016
12 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Date:2015
Deposited On:22 Feb 2016 13:16
Last Modified:05 Apr 2016 20:04
Publisher:De Gruyter Open
Number of Pages:11
ISSN:2081-4836
Publisher DOI:https://doi.org/10.1515/pjbr-2015-0011

Download

Download PDF  'Learning the condition of satisfaction of an elementary behavior in dynamic field theory'.
Preview
Content: Published Version
Filetype: PDF
Size: 1MB
View at publisher
Licence: Creative Commons: Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)