A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning
The paper proposes a biologically-inspired cognitive agent model, known as FALCON-X, based on an integration of the Adaptive Control of Thought (ACT-R) architecture and a class of self-organizing neural networks called fusion Adaptive Resonance Theory (fusion ART). By replacing the production system...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2010
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6252 https://ink.library.smu.edu.sg/context/sis_research/article/7255/viewcontent/BICA_IAT_2010.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-7255 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-72552021-11-10T04:12:03Z A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning TAN, Ah-hwee NG, Gee-Wah The paper proposes a biologically-inspired cognitive agent model, known as FALCON-X, based on an integration of the Adaptive Control of Thought (ACT-R) architecture and a class of self-organizing neural networks called fusion Adaptive Resonance Theory (fusion ART). By replacing the production system of ACT-R by a fusion ART model, FALCON-X integrates high-level deliberative cognitive behaviors and real-time learning abilities, based on biologically plausible neural pathways. We illustrate how FALCON-X, consisting of a core inference area interacting with the associated intentional, declarative, perceptual, motor and critic memory modules, can be used to build virtual robots for battles in a simulated RoboCode domain. The performance of FALCON-X demonstrates the efficacy of the hybrid approach. 2010-09-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6252 info:doi/10.1109/WI-IAT.2010.210 https://ink.library.smu.edu.sg/context/sis_research/article/7255/viewcontent/BICA_IAT_2010.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University cognitive agents knowledge representation reinforcement learning Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
cognitive agents knowledge representation reinforcement learning Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing |
spellingShingle |
cognitive agents knowledge representation reinforcement learning Artificial Intelligence and Robotics Numerical Analysis and Scientific Computing TAN, Ah-hwee NG, Gee-Wah A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
description |
The paper proposes a biologically-inspired cognitive agent model, known as FALCON-X, based on an integration of the Adaptive Control of Thought (ACT-R) architecture and a class of self-organizing neural networks called fusion Adaptive Resonance Theory (fusion ART). By replacing the production system of ACT-R by a fusion ART model, FALCON-X integrates high-level deliberative cognitive behaviors and real-time learning abilities, based on biologically plausible neural pathways. We illustrate how FALCON-X, consisting of a core inference area interacting with the associated intentional, declarative, perceptual, motor and critic memory modules, can be used to build virtual robots for battles in a simulated RoboCode domain. The performance of FALCON-X demonstrates the efficacy of the hybrid approach. |
format |
text |
author |
TAN, Ah-hwee NG, Gee-Wah |
author_facet |
TAN, Ah-hwee NG, Gee-Wah |
author_sort |
TAN, Ah-hwee |
title |
A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
title_short |
A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
title_full |
A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
title_fullStr |
A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
title_full_unstemmed |
A biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
title_sort |
biologically-inspired cognitive agent model integrating declarative knowledge and reinforcement learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2010 |
url |
https://ink.library.smu.edu.sg/sis_research/6252 https://ink.library.smu.edu.sg/context/sis_research/article/7255/viewcontent/BICA_IAT_2010.pdf |
_version_ |
1770575910787874816 |