Modelling Learning for Intelligent Software Agents: A Connectionist Approach
Modelling Learning for Intelligent Software Agents: A Connectionist Approach
This paper aims to show how a connectionist model can provide a form of adaptive action selection mechanism (ASM) for reactive virtual agents. By adopting a horizontally layered control architecture, we can build an agent with the ability to learn associations between sensory input and internal state to produce and adapt predictions or responses. At the lowest level, stimuli are categorised by a plastic self-organising mechanism which then activates a prediction module. Subsequently, if the prediction module's action results in a harmful environmental consequence, a conditioning network (reflecting internal state) modifies the agent's choice of prediction during the remainder of its attempt to find the optimal action. This acquisition of behaviour is regulated by a control layer and finally, an application-specific layer.
143-46
Joyce, Dan W.
21018c91-19aa-4547-aa19-afefae6b661a
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
1999
Joyce, Dan W.
21018c91-19aa-4547-aa19-afefae6b661a
Lewis, Paul H.
7aa6c6d9-bc69-4e19-b2ac-a6e20558c020
Joyce, Dan W. and Lewis, Paul H.
(1999)
Modelling Learning for Intelligent Software Agents: A Connectionist Approach.
Proceedings of the Second Workshop on Intelligent Virtual Agents.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
This paper aims to show how a connectionist model can provide a form of adaptive action selection mechanism (ASM) for reactive virtual agents. By adopting a horizontally layered control architecture, we can build an agent with the ability to learn associations between sensory input and internal state to produce and adapt predictions or responses. At the lowest level, stimuli are categorised by a plastic self-organising mechanism which then activates a prediction module. Subsequently, if the prediction module's action results in a harmful environmental consequence, a conditioning network (reflecting internal state) modifies the agent's choice of prediction during the remainder of its attempt to find the optimal action. This acquisition of behaviour is regulated by a control layer and finally, an application-specific layer.
This record has no associated files available for download.
More information
Published date: 1999
Venue - Dates:
Proceedings of the Second Workshop on Intelligent Virtual Agents, 1999-01-01
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 252539
URI: http://eprints.soton.ac.uk/id/eprint/252539
PURE UUID: 3d1fa04c-1d9f-4553-aba6-62e3250221b4
Catalogue record
Date deposited: 22 Feb 2000
Last modified: 10 Dec 2021 20:27
Export record
Contributors
Author:
Dan W. Joyce
Author:
Paul H. Lewis
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics