ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper An Application of LSTM Recurrent Networks to Expanding of Search Tree Nodes in Symbolic Planning
Cited 1 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Joonmyun Cho, Young-Sung Son, Jun Hee Park, Chan-Won Park
Issue Date
2020-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1293-1295
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289296
Abstract
Applying deep learning to symbolic planning is not straightforward because they differently internalize knowledge. One represents knowledge numerically while the other does symbolically. Hybrid methods that take strengths from both techniques will deliver better performance on automated planning. This paper presents a method to improve the performance of symbolic planning by applying LSTM recurrent networks to inferring the guidance knowledge for search tree node expansion. The networks learn sequential patterns across previous node expansions and generalizes the learned knowledge to predict promising actions and their probability scores at the present expansion step. The prediction consists with node cost estimation for heuristic search. A simple experiment vindicates the method of this research.
KSP Keywords
Automated Planning, Heuristic search, Recurrent Network(RN), Sequential patterns, cost estimation, deep learning(DL), hybrid method, search tree