How to autonomously decide boundary between self and others?

Author

Takadama, Keiki ; Inoue, Hiroyasu ; Shimohara, Katsunori

Author_Institution

ATR Int., Kyoto, Japan

Volume

4

fYear

2000

fDate

2000

Firstpage

2903

Abstract

This paper extends the learning classifier system. (LCS) to introduce the mechanism for recognizing a current situation by determining a boundary between self and others, and investigates its effectiveness in an interaction with an agent. Intensive simulations for adapting an interacting agent by acquiring its internal model have revealed the following implications: (1) the proposed mechanism. gives a higher adaptation to the integrating agent than a random mechanism, the conventional LCS, and previously proposed mechanisms; (2) the proposed mechanism keeps its effectiveness, even in a complex internal model of an. agent; and (3) the proposed mechanism has the potential to provide autonomy in terms of the precise recognition of the current situation

Keywords

adaptive systems; learning (artificial intelligence); learning systems; pattern classification; simulation; software agents; agent; autonomous boundary decision; complex internal model; current situation recognition; interacting agent adaptation; internal model; learning classifier system; simulations; Cost accounting; Humans; Inference mechanisms; Production systems; Zero current switching;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics Society, 2000. IECON 2000. 26th Annual Confjerence of the IEEE

Conference_Location

Nagoya

Print_ISBN

0-7803-6456-2

Type

conf

DOI

10.1109/IECON.2000.972459

Filename

972459