DocumentCode :
3102471
Title :
Plans as Products of Learning
Author :
Karim, Samin ; Subagdja, Budhitama ; Sonenberg, Liz
Author_Institution :
Dept. of Inf. Syst., Univ. of Melbourne, Melbourne, VIC
fYear :
2006
fDate :
18-22 Dec. 2006
Firstpage :
139
Lastpage :
145
Abstract :
This paper presents motivations and current related work in the field of plan learning. Additionally, two approaches that achieve plan learning are presented. The two presented approaches are centred on the BDI framework of agency and have particular focus on plans, which, alongside goals, are the means to fulfil intentions in most pragmatic and theoretical realisations of the BDI framework. The first approach is a hybrid architecture that combines a BDI plan extractor and executor with a generic low-level learner. The second approach uses hypotheses to suggest incremental refinements of a priori plans. Both approaches achieve plan generation that is a result of experiential learning. We conclude by discussing issues related to these two approaches, and from other related work.
Keywords :
learning (artificial intelligence); planning (artificial intelligence); BDI framework; experiential learning; plan generation; plan learning; Artificial neural networks; Engines; Humans; Information systems; Intelligent agent; Learning; Mobile robots; Neural networks; Process planning; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Agent Technology, 2006. IAT '06. IEEE/WIC/ACM International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2748-5
Type :
conf
DOI :
10.1109/IAT.2006.100
Filename :
4052912
Link To Document :
بازگشت