TitleLong-Term Symbolic Learning in Soar and ACT-R
Publication TypeConference Proceedings
Year of Conference2006
AuthorsKennedy, WG, Trafton, JG
Conference NameSeventh International Conference on Cognitive Modeling
Pagination166-171
Date Published01/2006
Conference LocationTrieste, Italy
Abstract

The characteristics of long-term, symbolic learning were investigated using Soar and ACT-R models of a task to rearrange blocks into specific configurations. Long sequences of problems were run collecting data to answer fundamental questions about long-term, symbolic learning. The questions were whether symbolic learning continues indefinitely, how learned knowledge is used, and whether performance degrades over the long term. It was found that in both systems symbolic learning eventually stopped, ACT-R produced three observable phases of learning, and both Soar and ACT-R suffer from the utility problem of degraded performance with continuous on-line learning.

Full Text
NRL Publication Release Number: 
06-1226-0243