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...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/98594 http://hdl.handle.net/10220/13656 |
| _version_ | 1826110361410994176 |
|---|---|
| author | Subagdja, Budhitama Tan, Ah-Hwee |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Subagdja, Budhitama Tan, Ah-Hwee |
| author_sort | Subagdja, Budhitama |
| collection | NTU |
| 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. |
| first_indexed | 2024-10-01T02:33:08Z |
| format | Journal Article |
| id | ntu-10356/98594 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:33:08Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/985942020-05-28T07:17:56Z iFALCON : a neural architecture for hierarchical planning Subagdja, Budhitama Tan, Ah-Hwee School of Computer Engineering DRNTU::Engineering::Computer science and engineering 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. 2013-09-24T07:23:45Z 2019-12-06T19:57:12Z 2013-09-24T07:23:45Z 2019-12-06T19:57:12Z 2012 2012 Journal Article Subagdja, B., & Tan, A. H. (2012). iFALCON : a neural architecture for hierarchical planning. Neurocomputing, 86, 124-139. https://hdl.handle.net/10356/98594 http://hdl.handle.net/10220/13656 10.1016/j.neucom.2012.01.008 en Neurocomputing |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Subagdja, Budhitama Tan, Ah-Hwee iFALCON : a neural architecture for hierarchical planning |
| title | 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_short | iFALCON : a neural architecture for hierarchical planning |
| title_sort | ifalcon a neural architecture for hierarchical planning |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/98594 http://hdl.handle.net/10220/13656 |
| work_keys_str_mv | AT subagdjabudhitama ifalconaneuralarchitectureforhierarchicalplanning AT tanahhwee ifalconaneuralarchitectureforhierarchicalplanning |