Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/96713
Title: Motivated learning for the development of autonomous systems
Authors: Starzyk, Janusz A.
Graham, James T.
Raif, Pawel
Tan, Ah-Hwee
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2011
Source: Starzyk, J. A., Graham, J. T., Raif, P.,& Tan, A. H. (2012). Motivated learning for the development of autonomous systems. Cognitive Systems Research, 14(1), 10-25.
Series/Report no.: Cognitive systems research
Abstract: A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine’s behavior based on competition between dynamically-changing pain signals. This provides an interplay of externally driven and internally generated control signals. It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in dynamically-changing environments. In addition, this paper shows the basic neural network structures used to create abstract motivations, higher level goals, and subgoals. Finally, simulation results show comparisons between ML and RL in environments of gradually increasing sophistication and levels of difficulty.
URI: https://hdl.handle.net/10356/96713
http://hdl.handle.net/10220/13056
ISSN: 1389-0417
DOI: http://dx.doi.org/10.1016/j.cogsys.2010.12.009
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.