Artificial emotion model based on reinforcement learning mechanism of neural network

Abstract A hierarchical-processed frame construction of artificial emotion model for intelligent system is proposed in the paper according to the basic conclusion of emotional psychology. The general method of emotion processing, which considers only one single layer, has been changed in the presented construction. An artificial emotional development model is put forward based on reinforcement learning mechanism of neural network. The new model takes the emotion itself as reinforcement signal and describes its different influences on action learning efficiency corresponding to different individualities. In the end, simulation result based on child playmate robot is discussed and the effectiveness of the model is verified.

[1]  Rosalind W. Picard.  Affective Computing , 1997 .

[2]  Zhen Liu.  A Personality Based Emotion Model for Intelligent Virtual Agents , 2008, 2008 Fourth International Conference on Natural Computation.

[3]  M. Mitchell Waldrop,et al.  Complexity : the emerging science and the edge of order and chaos , 1992 .

[4]  Seung-Ik Lee,et al.  Neurocognitive Affective System for an Emotive Robot , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[6]  Pan Zhigeng,et al.  A Comprehensive Computational Model of Emotions , 2008 .

[7]  Aaron Sloman,et al.  Varieties of Affect and the CogAff Architecture Schema , 2001 .

[8]  Christine L. Lisetti,et al.  Multilevel Emotion Modeling for Autonomous Agents , 2004, AAAI Technical Report.

[9]  K. Strongman,et al.  The psychology of emotion , 1973 .

[10]  Colin G. Johnson.  Proceedings of the AISB'01 Symposium on Emotion, Cognition and Affective Computing , 2001 .

[11]  Masahiro Fujita,et al.  Ethological modeling and architecture for an entertainment robot , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).