Extending the Soar Cognitive Architecture

被引：0

作者：

Laird, John E. ^{[1
]}

机构：

[1] Univ Michigan, Div Comp Sci & Engn, Ann Arbor, MI 48109 USA

来源：

ARTIFICIAL GENERAL INTELLIGENCE 2008 | 2008年 / 171卷

关键词：

Soar; cognitive architecture; reinforcement learning; episodic memory; semantic memory; clustering; mental imagery; emotion;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One approach in pursuit of general intelligent agents has been to concentrate on the underlying cognitive architecture, of which Soar is a prime example. In the past, Soar has relied on a minimal number of architectural modules together with purely symbolic representations of knowledge. This paper presents the cognitive architecture approach to general intelligence and the traditional, symbolic Soar architecture. This is followed by major additions to Soar: non-symbolic representations, new learning mechanisms, and long-term memories.

引用

页码：224 / 235

页数：12

共 31 条

[1]

[Anonymous], 2007, CAN HUMAN MIND OCCUR, DOI DOI 10.1093/ACPROF:OSO/9780195324259.001.0001

[2]

[Anonymous], 1983, CANADIAN PSYCHOL

[3]

Chentanez N., 2004, Advances in Neural Information Processing Systems, V17

[4]

CHO BH, 1991, PROGRAM OF THE THIRTEENTH ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, P673

[5]

CHONG R, 2003, P 5 INT C COGN MOD P

[6]

Granger R, 2006, AI MAG, V27, P15

[7]

Gratch J., 2004, Journal of Cognitive Systems Research, V5, P269, DOI DOI 10.1016/J.COGSYS.2004.02.002

[8]

JONES RM, 1999, AI MAG, V20, P2741

[9]

Kieras DE, 1997, HUM-COMPUT INTERACT, V12, P391, DOI 10.1207/s15327051hci1204_4

[10]

Kosslyn S.M., 2006, The case for mental imagery

← 1 2 3 4 →