A self-organizing neural architecture integrating desire, intention and reinforcement learning
This paper presents a self-organizing neural architecture that integrates the features of belief, desire, and intention (BDI) systems with reinforcement learning. Based on fusion Adaptive Resonance Theory (fusion ART), the proposed architecture provides a unified treatment for both intentional and r...
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/5217 https://ink.library.smu.edu.sg/context/sis_research/article/6220/viewcontent/1_s2.0_S0925231209004196_main.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-6220 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-62202020-07-23T18:36:05Z A self-organizing neural architecture integrating desire, intention and reinforcement learning TAN, Ah-hwee FENG, Yu-Hong ONG, Yew-Soon This paper presents a self-organizing neural architecture that integrates the features of belief, desire, and intention (BDI) systems with reinforcement learning. Based on fusion Adaptive Resonance Theory (fusion ART), the proposed architecture provides a unified treatment for both intentional and reactive cognitive functionalities. Operating with a sense-act-learn paradigm, the low level reactive module is a fusion ART network that learns action and value policies across the sensory, motor, and feedback channels. During performance, the actions executed by the reactive module are tracked by a high level intention module (also a fusion ART network) that learns to associate sequences of actions with context and goals. The intention module equips the architecture with deliberative planning capabilities, enabling it to purposefully maintain an agenda of actions to perform and to reduce the need of constantly sensing the environment. Through reinforcement learning, plans can also be evaluated and refined without the rigidity of user-defined plans. We examine two strategies for combining the intention and reactive modules for decision making in a real time environment. Our experiments based on a minefield navigation domain show that the integrated architecture is able to learn plans efficiently, achieve good plan utilization, and combine both intentional and reactive action execution to yield a robust performance. 2010-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5217 info:doi/10.1016/j.neucom.2009.11.012 https://ink.library.smu.edu.sg/context/sis_research/article/6220/viewcontent/1_s2.0_S0925231209004196_main.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 Reinforcement learning Plan learning Self-organizing neural networks BDI Minefield navigation Computer and Systems Architecture Databases and Information Systems OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Reinforcement learning Plan learning Self-organizing neural networks BDI Minefield navigation Computer and Systems Architecture Databases and Information Systems OS and Networks |
spellingShingle |
Reinforcement learning Plan learning Self-organizing neural networks BDI Minefield navigation Computer and Systems Architecture Databases and Information Systems OS and Networks TAN, Ah-hwee FENG, Yu-Hong ONG, Yew-Soon A self-organizing neural architecture integrating desire, intention and reinforcement learning |
description |
This paper presents a self-organizing neural architecture that integrates the features of belief, desire, and intention (BDI) systems with reinforcement learning. Based on fusion Adaptive Resonance Theory (fusion ART), the proposed architecture provides a unified treatment for both intentional and reactive cognitive functionalities. Operating with a sense-act-learn paradigm, the low level reactive module is a fusion ART network that learns action and value policies across the sensory, motor, and feedback channels. During performance, the actions executed by the reactive module are tracked by a high level intention module (also a fusion ART network) that learns to associate sequences of actions with context and goals. The intention module equips the architecture with deliberative planning capabilities, enabling it to purposefully maintain an agenda of actions to perform and to reduce the need of constantly sensing the environment. Through reinforcement learning, plans can also be evaluated and refined without the rigidity of user-defined plans. We examine two strategies for combining the intention and reactive modules for decision making in a real time environment. Our experiments based on a minefield navigation domain show that the integrated architecture is able to learn plans efficiently, achieve good plan utilization, and combine both intentional and reactive action execution to yield a robust performance. |
format |
text |
author |
TAN, Ah-hwee FENG, Yu-Hong ONG, Yew-Soon |
author_facet |
TAN, Ah-hwee FENG, Yu-Hong ONG, Yew-Soon |
author_sort |
TAN, Ah-hwee |
title |
A self-organizing neural architecture integrating desire, intention and reinforcement learning |
title_short |
A self-organizing neural architecture integrating desire, intention and reinforcement learning |
title_full |
A self-organizing neural architecture integrating desire, intention and reinforcement learning |
title_fullStr |
A self-organizing neural architecture integrating desire, intention and reinforcement learning |
title_full_unstemmed |
A self-organizing neural architecture integrating desire, intention and reinforcement learning |
title_sort |
self-organizing neural architecture integrating desire, intention and reinforcement learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2010 |
url |
https://ink.library.smu.edu.sg/sis_research/5217 https://ink.library.smu.edu.sg/context/sis_research/article/6220/viewcontent/1_s2.0_S0925231209004196_main.pdf |
_version_ |
1770575336208072704 |