Learning Causality on Action Language A.

Accession number;99A0263649
Title;Learning Causality on Action Language A.
Author; NABESHIMA HIDETOMO (Kobe Univ., Grad. Sch.) INOUE KATSUMI (Kobe Univ., Grad. Sch.) HANEDA HIROMASA (Kobe Univ., Grad. Sch.)
Journal Title;IEIC Technical Report (Institute of Electronics, Information and Communication Engineers)
Journal Code:S0532B
ISSN:0913-5685
VOL.98;NO.498(AI98 62-67);PAGE.41-46(1999)
Figure&Table&Reference;FIG.4, REF.9
Pub. Country;Japan
Language;Japanese
Abstract;Autonomous agents that behave in dynamic world needs the learning ability that can acquire knowledge about the environment in which the agents have never encountered. In this paper, we investigate a learning algorithm which produces rules about effects of actions from observations in action language A. (author abst.)