A hybrid architecture combining reactive plan execution and reactive learning
Developing software agents has been complicated by the problem of how knowledge should be represented and used. Many researchers have identified that agents need not require the use of complex representations, but in many cases suffice to use “the world” as their representation. However, the problem...
Saved in:
Main Authors: | , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2006
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6699 https://ink.library.smu.edu.sg/context/sis_research/article/7702/viewcontent/LNAI_4099___PRICAI_2006__Trends_in_Artificial_Intelligence.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-7702 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-77022023-08-21T06:23:36Z A hybrid architecture combining reactive plan execution and reactive learning KARIM, Samin SONENBERG, Liz TAN, Ah-Hwee Developing software agents has been complicated by the problem of how knowledge should be represented and used. Many researchers have identified that agents need not require the use of complex representations, but in many cases suffice to use “the world” as their representation. However, the problem of introspection, both by the agents themselves and by (human) domain experts, requires a knowledge representation with a higher level of abstraction that is more ‘understandable’. Learning and adaptation in agents has traditionally required knowledge to be represented at an arbitrary, low-level of abstraction. We seek to create an agent that has the capability of learning as well as utilising knowledge represented at a higher level of abstraction. We firstly explore a reactive learner (Falcon) and reactive plan execution engine based on BDI (JACK) through experiments and analysis. We then describe an architecture we have developed that combines the BDI framework to the low-level reinforcement learner and present promising results from experiments using our minefield navigation domain. 2006-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6699 info:doi/10.1007/978-3-540-36668-3_23 https://ink.library.smu.edu.sg/context/sis_research/article/7702/viewcontent/LNAI_4099___PRICAI_2006__Trends_in_Artificial_Intelligence.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 Learner Multiagent System Domain Expert Navigation Task Hybrid Architecture Databases and Information Systems Systems Architecture |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Reinforcement Learner Multiagent System Domain Expert Navigation Task Hybrid Architecture Databases and Information Systems Systems Architecture |
spellingShingle |
Reinforcement Learner Multiagent System Domain Expert Navigation Task Hybrid Architecture Databases and Information Systems Systems Architecture KARIM, Samin SONENBERG, Liz TAN, Ah-Hwee A hybrid architecture combining reactive plan execution and reactive learning |
description |
Developing software agents has been complicated by the problem of how knowledge should be represented and used. Many researchers have identified that agents need not require the use of complex representations, but in many cases suffice to use “the world” as their representation. However, the problem of introspection, both by the agents themselves and by (human) domain experts, requires a knowledge representation with a higher level of abstraction that is more ‘understandable’. Learning and adaptation in agents has traditionally required knowledge to be represented at an arbitrary, low-level of abstraction. We seek to create an agent that has the capability of learning as well as utilising knowledge represented at a higher level of abstraction. We firstly explore a reactive learner (Falcon) and reactive plan execution engine based on BDI (JACK) through experiments and analysis. We then describe an architecture we have developed that combines the BDI framework to the low-level reinforcement learner and present promising results from experiments using our minefield navigation domain. |
format |
text |
author |
KARIM, Samin SONENBERG, Liz TAN, Ah-Hwee |
author_facet |
KARIM, Samin SONENBERG, Liz TAN, Ah-Hwee |
author_sort |
KARIM, Samin |
title |
A hybrid architecture combining reactive plan execution and reactive learning |
title_short |
A hybrid architecture combining reactive plan execution and reactive learning |
title_full |
A hybrid architecture combining reactive plan execution and reactive learning |
title_fullStr |
A hybrid architecture combining reactive plan execution and reactive learning |
title_full_unstemmed |
A hybrid architecture combining reactive plan execution and reactive learning |
title_sort |
hybrid architecture combining reactive plan execution and reactive learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2006 |
url |
https://ink.library.smu.edu.sg/sis_research/6699 https://ink.library.smu.edu.sg/context/sis_research/article/7702/viewcontent/LNAI_4099___PRICAI_2006__Trends_in_Artificial_Intelligence.pdf |
_version_ |
1779156892618063872 |