Operant Conditioning Learning Model in the Bionic Experiment

Abstract:

A learning model based on the operant conditioning mechanism (OCLM) is presented in this paper to deal with the autonomous learning problem in cognitive robotics. The model is described by 9 elements, including the space set, the action set, the bionic learning function and the system entropy etc. To describe the learning mechanism which is the core of the model, a new notion negative ideal degree(NID) is defined. We also prove the convergence of OCLM to indicate that the model is a self-organization system. OCLM has been applied to simulating the Skinner rat experiment. The results show that this model can well simulate the animals operant conditioning behavior, acquire the cognitive skills through the interaction with the environment and achieve self-learning and self-adaptability.

• Periodical: Applied Mechanics and Materials (Volumes 373-375)
• Pages: 255-264
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.373-375.255
• Online since: August 2013
• Authors: Jing Huang, Xiao Gang Ruan, Qing Wu Fan, Xiao Ping Zhang
• Keywords: Autonomous Learning, Cognitive Robotics, Operant Conditioning Learning Model, Skinner Rat Experiment

References

[1] H.W. Li, J.Y. Xiao: Journal of Dialectics of Nature. Vol. 28(1) (2006), p.29 (In Chinese).

[2] R. A. Brooks: IEEE J. Robotics and Automation. Vol. 2(1) (1986), p.14.

[3] R.A. Brooks: Artificial Intelligence. Vol. 47(1)(1991), p.139.

[4] J. Weng, J. Mcclelland, A. Pentland et al.: Science. Vol. 291(2001), p.599.

[5] B.F. Skinner, in: The Behavior of organisms: an experimental analysis (Appleton-Century Company, New York 1938).

[6] P. Gaudiano, C. Chang: IEEE International Symposium on Computational Intelligence in Robotics and Automation (1997), p.13.

[7] P. Gaudiano, E. Zalama, C. Chang and J. L. Coronado: From Animals to Animats 4(1996), p.373.

[8] D.S. Touretzky and L.M. Saksida: Adaptive Behavior  Vol. 5 No. 3-4 (1997), p.219.

[9] P. MANOONPONG, C. KOLODZIEJSKI, F. WÖRGÖTTER and J. MORIMOTO: Advances in Complex Systems(2013), in press.

[10] X.G. Ruan, J.X. Cai and L.Z. Dai: Journal of Beijing University of Technology Vol. 36 No. 8 (2010), p.1025 (In Chinese).

[11] X.G. Ruan, L.Z. Dai, N.G. Yu and J.J. Yu: Control Theory & Applications Vol. 29 No. 11(2012), p.1452(In Chinese).