Title :
Autonomy from the viewpoint of bi-referential model
Author :
Shiose, Takayuki ; Sawaragi, Tetsuo ; Katai, Osamu ; Okada, Michio
Author_Institution :
Graduate Sch. of Eng., Kyoto Univ., Japan
Abstract :
The paper discusses agents´ autonomous learning. Although the viewpoints of the agent have been given by a designer in conventional learning models, the agent ought to be able to replace its own viewpoints by itself in a real sense so the agent has autonomy. It is assumed that an autonomous agent should be equipped with the following three characteristics; (a) self-generation of goals and evaluation criteria, (b) sense of values, (c) boundary setting between self and others. Especially, the discussion focuses on acquiring the process of the second characteristic, (b) sense of values, by proposing a Bi-Referential Model, which, is based on developmental psychology. We discuss how the segregating processes of sense of values are dependent on the competition of shared resources, and how the Bi-Referential Model can reenact such segregating processes. Then we compare our approach with some related works and explain the major differences
Keywords :
learning (artificial intelligence); modelling; multi-agent systems; agent autonomous learning; autonomous agent; bi-referential model; boundary setting; conventional learning models; developmental psychology; evaluation criteria; goal self-generation; segregating processes; sense of values; shared resources; Autonomous agents; Decision making; Machine learning; Psychology;
Conference_Titel :
Industrial Electronics Society, 2000. IECON 2000. 26th Annual Confjerence of the IEEE
Conference_Location :
Nagoya
Print_ISBN :
0-7803-6456-2
DOI :
10.1109/IECON.2000.972455