On the effects of node duplication and connection-oriented constructivism in neural XCSF

ABSTRACT

For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility guided by the environment at any given time. This paper presents the use of constructivism-inspired mechanisms within a neural learning classifier system which exploits parameter self-adaptation as an approach to realize such behavior. Various network growth/regression mechanisms are implemented and their performances compared. The system uses a rule structure in which each is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the system.

REFERENCES

• 1: Ahluwalia, M. & Bull, L. 1999. A Genetic Programming Classifier System. In W. Banzhaf, J. Daida, A.E. Eiben, M.H. Garzon, V. Honavar, M. Jakiela & R.E. Smith (eds) Proceedings of the Genetic and Evolutionary Computation Conference - GECCO-99. San Mateo, CA: Morgan Kaufmann, pp11--18.
• 2: Larry Bull , Toby O'Hara, Accuracy-based Neuro And Neuro-fuzzy Classifier Systems, Proceedings of the Genetic and Evolutionary Computation Conference, p.905-911, July 09-13, 2002
• 3: Larry Bull, On Using Constructivism in Neural Classifier Systems, Proceedings of the 7th International Conference on Parallel Problem Solving from Nature, p.558-567, September 07-11, 2002
• 4: Bull, L., Hurst, J., & Tomlinson, A. 2000. Self-Adaptive Mutation in Classifier System Controllers. In J-A. Meyer, A. Berthoz, D. Floreano, H. Roitblatt & S.W. Wilson (Eds.) From Animals to Animats 6 - The Sixth International Conference on the Simulation of Adaptive Behaviour, MIT Press.
• 5: Martin Butz , Stewart W. Wilson, An Algorithmic Description of XCS, Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems, p.253-272, September 15-16, 2000
• 6: Cordón, O., Herrera, F., Hoffmann, F. & Magdalena, L. 2001. Genetic Fuzzy Systems. Evolutionary Tuning and Learning of Fuzzy Knowledge Bases. World Scientific.
• 7: Edelman, G. 1987. Neural Darwinism: The Theory of Neuronal Group Selection. New York: Basic Books.
• 8: Harvey, I. 1992. Species Adaptation Genetic Algorithms: A Basis for a Continuing SAGA. In F. Varela & P. Bourgine (eds) Proceedings of 1st European Conference on Artificial Life. MIT Press, pp346--354
• 9: John H. Holland, Adaptation in natural and artificial systems, MIT Press, Cambridge, MA, 1992
• 10: Holland, J.H. 1976. Adaptation. In R. Rosen & F.M. Snell (Eds.) Progress in Theoretical Biology 4. New York: Academic Press, pp263--293.
• 11: Gerard D. Howard , Larry Bull , Pier-Luca Lanzi, Self-adaptive constructivism in Neural XCS and XCSF, Proceedings of the 10th annual conference on Genetic and evolutionary computation, July 12-16, 2008, Atlanta, GA, USA [doi>10.1145/1389095.1389364]
• 12: Jacob Hurst , Larry Bull, A Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control, Artificial Life, v.12 n.3, p.353-380, July 2006 [doi>10.1162/artl.2006.12.3.353]
• 13: Hutt, B.; Warwick, K. 2007. Synapsing Variable-Length Crossover: Meaningful Crossover for Variable-Length Genomes, Evolutionary Computation, IEEE Transactions on , vol.11, no.1, pp.118--131
• 14: Pier Luca Lanzi , Daniele Loiacono, Classifier systems that compute action mappings, Proceedings of the 9th annual conference on Genetic and evolutionary computation, July 07-11, 2007, London, England [doi>10.1145/1276958.1277322]
• 15: Pier Luca Lanzi, An analysis of generalization in the xcs classifier system, Evolutionary Computation, v.7 n.2, p.125-149, Summer 1999 [doi>10.1162/evco.1999.7.2.125]
• 16: Maynard Smith, J. & Szathmary, E. 1995. The Major Transitions in Evolution. W.H. Freeman
• 17: Quartz, S.R. & Sejnowski, T.J. 1997. The Neural Basis of Cognitive Development: A Constructionist Manifesto. Behavioural and Brain Sciences 20(4): 537--596.
• 18: Rechenberg, I. 1973. Evolutionsstrategie-Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Fommann-Holzboog, Stuttgart
• 19: David E. Rumelhart , James L. McClelland , CORPORATE PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 20: Schlessinger, E., Bentley, P. J. and Lotto, R. B. 2005. Analysing the Evolvability of Neural Network Agents through Structural Mutations. Proc. of European Conference on Artificial Life (ECAL 2005), September 5-9, 2005, Canterbury, UK.
• 21: Karlheinz Schmitt, Using gene deletion and gene duplication in evolution strategies, Proceedings of the 2005 conference on Genetic and evolutionary computation, June 25-29, 2005, Washington DC, USA [doi>10.1145/1068009.1068164]
• 22: Matthew Studley , Larry Bull, Using the XCS Classifier System for Multi-objective Reinforcement Learning Problems, Artificial Life, v.13 n.1, p.69-86, Winter 2007 [doi>10.1162/artl.2007.13.1.69]
• 23: Stewart W. Wilson, Zcs: A zeroth level classifier system, Evolutionary Computation, v.2 n.1, p.1-18, Spring 1994 [doi>10.1162/evco.1994.2.1.1]
• 24: Stewart W. Wilson, Classifier fitness based on accuracy, Evolutionary Computation, v.3 n.2, p.149-175, Summer 1995 [doi>10.1162/evco.1995.3.2.149]
• 25: Wilson, S.W. 2001. Function Approximation with a Classifier System. In Spector, L., D., G. E., Wu, A., Langdon, W.B., Voight, H. M., and Gen, M., (Eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 01) Morgan Kaufmann. pp 974--981
• 26: Wilson, S.W. 2007. Three architectures for continuous action Learning Classifier Systems. International Workshops, IWLCS 2003-2005, Revised Selected Papers. In T. Kovacs, X. Llorà, K. Takadama, P. L. Lanzi, W. Stolzmann, S. W. Wilson (Eds.) Lecture Notes in Artificial Intelligence (LNAI-4399),. Berlin, Springer-Verlag. pp. 239--257

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Knowledge acquisition

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
          Subjects: Concept learning; Connectionism and neural nets

General Terms:
Experimentation

Keywords:
constructivism, learning classifier systems, neural networks, reinforcement learning, self-adaptation