iFALCON: A neural architecture for hierarchical planning

Hierarchical planning is an approach of planning by composing and executing hierarchically arranged predefined plans on the fly to solve some problems. This approach commonly relies on a domain expert providing all semantic and structural knowledge. One challenge is how the system deals with incompl...

Full description

Saved in:
Bibliographic Details
Main Authors: SUBAGDJA, Budhitama, TAN, Ah-hwee
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2012
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5222
https://ink.library.smu.edu.sg/context/sis_research/article/6225/viewcontent/1_s2.0_S092523121200094X_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-6225
record_format dspace
spelling sg-smu-ink.sis_research-62252020-07-23T18:33:08Z iFALCON: A neural architecture for hierarchical planning SUBAGDJA, Budhitama TAN, Ah-hwee Hierarchical planning is an approach of planning by composing and executing hierarchically arranged predefined plans on the fly to solve some problems. This approach commonly relies on a domain expert providing all semantic and structural knowledge. One challenge is how the system deals with incomplete ill-defined knowledge while the solution can be achieved on the fly. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, in some cases, it is still difficult to produce the appropriate knowledge due to the complexity of the problem domain especially if the missing knowledge must be acquired online. This paper presents a novel neural-based model of hierarchical planning that can seek and acquire new plans online if the necessary knowledge are lacking. It enables all propositions and descriptions of plans to be computed and learnt simultaneously as inherent features of the model rather than discretely processed like in most symbolic approaches. Using a multi-channel adaptive resonance theory (fusion ART) neural network as the basic building block of the architecture and a new representation technique called gradient encoding, the so-called iFALCON architecture can capture and manipulate sequential and hierarchical relations of plans on the fly. Case studies using blocks world domain and an agent in Unreal Tournament video game demonstrate that the model can be used to execute, plan, and discover new plans through experiences. 2012-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5222 info:doi/10.1016/j.neucom.2012.01.008 https://ink.library.smu.edu.sg/context/sis_research/article/6225/viewcontent/1_s2.0_S092523121200094X_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 Hierarchical planning Plan learning Adaptive resonance theory Computer and Systems Architecture Computer Engineering Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Hierarchical planning
Plan learning
Adaptive resonance theory
Computer and Systems Architecture
Computer Engineering
Databases and Information Systems
spellingShingle Hierarchical planning
Plan learning
Adaptive resonance theory
Computer and Systems Architecture
Computer Engineering
Databases and Information Systems
SUBAGDJA, Budhitama
TAN, Ah-hwee
iFALCON: A neural architecture for hierarchical planning
description Hierarchical planning is an approach of planning by composing and executing hierarchically arranged predefined plans on the fly to solve some problems. This approach commonly relies on a domain expert providing all semantic and structural knowledge. One challenge is how the system deals with incomplete ill-defined knowledge while the solution can be achieved on the fly. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, in some cases, it is still difficult to produce the appropriate knowledge due to the complexity of the problem domain especially if the missing knowledge must be acquired online. This paper presents a novel neural-based model of hierarchical planning that can seek and acquire new plans online if the necessary knowledge are lacking. It enables all propositions and descriptions of plans to be computed and learnt simultaneously as inherent features of the model rather than discretely processed like in most symbolic approaches. Using a multi-channel adaptive resonance theory (fusion ART) neural network as the basic building block of the architecture and a new representation technique called gradient encoding, the so-called iFALCON architecture can capture and manipulate sequential and hierarchical relations of plans on the fly. Case studies using blocks world domain and an agent in Unreal Tournament video game demonstrate that the model can be used to execute, plan, and discover new plans through experiences.
format text
author SUBAGDJA, Budhitama
TAN, Ah-hwee
author_facet SUBAGDJA, Budhitama
TAN, Ah-hwee
author_sort SUBAGDJA, Budhitama
title iFALCON: A neural architecture for hierarchical planning
title_short iFALCON: A neural architecture for hierarchical planning
title_full iFALCON: A neural architecture for hierarchical planning
title_fullStr iFALCON: A neural architecture for hierarchical planning
title_full_unstemmed iFALCON: A neural architecture for hierarchical planning
title_sort ifalcon: a neural architecture for hierarchical planning
publisher Institutional Knowledge at Singapore Management University
publishDate 2012
url https://ink.library.smu.edu.sg/sis_research/5222
https://ink.library.smu.edu.sg/context/sis_research/article/6225/viewcontent/1_s2.0_S092523121200094X_main.pdf
_version_ 1770575337817636864