Consideration of Multiple Objectives in Neural Learning Classifier Systems

For effective use in a number of problem domains Learning Classifier Systems must be able to manage multiple objectives. This paper explicitly considers the case of developing the controller for a simulated mobile autonomous robot which must achieve a given task whilst maintaining sufficient battery power. A form of Learning Classifier System in which each rule is represented by an artificial neural network is used. Results are presented which show it is possible to solve both objectives when the energy level is presented as an input along with sensor data. A more realistic, and hence more complex, version of the basic scenario is then investigated.

[1]  Risto Miikkulainen,et al.  Forming Neural Networks Through Efficient and Adaptive Coevolution , 1997, Evolutionary Computation.

[2]  A. Martin V. Butz,et al.  The anticipatory classifier system and genetic generalization , 2002, Natural Computing.

[3]  Larry Bull,et al.  ZCS: Theory and practice: UWE Learning Classifier Systems Group Technical Report 01 , 2001 .

[4]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[5]  Larry Bull,et al.  Learning Classifier Systems , 2002, Annual Conference on Genetic and Evolutionary Computation.

[6]  Manuel Valenzuela-Rendón,et al.  The Fuzzy Classifier System: A Classifier System for Continuously Varying Variables , 1991, ICGA.

[7]  Marco Laumanns,et al.  A Tutorial on Evolutionary Multiobjective Optimization , 2004, Metaheuristics for Multiobjective Optimisation.

[8]  Stewart W. Wilson,et al.  Toward Optimal Classifier System Performance in Non-Markov Environments , 2000, Evolutionary Computation.

[9]  Zbigniew Michalewicz,et al.  Evolutionary Computation 1 , 2018 .

[10]  David H. Ackley,et al.  Interactions between learning and evolution , 1991 .

[11]  Jonas Karlsson,et al.  Learning to Solve Multiple Goals , 1997 .

[12]  Lawrence Davis,et al.  Mapping Neural Networks into Classifier Systems , 1989, ICGA.

[13]  Robert E. Smith,et al.  Is a Learning Classifier System a Type of Neural Network? , 1994, Evolutionary Computation.

[14]  Dale Schuurmans,et al.  Representational Difficulties with Classifier Systems , 1989, ICGA.

[15]  L. Darrell Whitley,et al.  Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect , 1993, Evolutionary Computation.

[16]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[17]  Larry Bull,et al.  On accuracy-based fitness , 2002, Soft Comput..

[18]  Kalyanmoy Deb,et al.  Multi-objective optimization using evolutionary algorithms , 2001, Wiley-Interscience series in systems and optimization.

[19]  Zbigniew Michalewicz,et al.  Evolutionary Computation 2 , 2000 .

[20]  Stewart W. Wilson.  State of XCS Classifier System Research , 1999, Learning Classifier Systems.

[21]  Larry Bull,et al.  A Genetic Programming-based Classifier System , 1999, GECCO.

[22]  Stewart W. Wilson.  ZCS: A Zeroth Level Classifier System , 1994, Evolutionary Computation.

[23]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[24]  Stewart W. Wilson.  Classifier Fitness Based on Accuracy , 1995, Evolutionary Computation.

[25]  Jürgen Schmidhuber,et al.  HQ-Learning , 1997, Adapt. Behav..

[26]  Marco Dorigo,et al.  A comparison of Q-learning and classifier systems , 1994 .

[27]  Dave Cliff,et al.  Adding Temporary Memory to ZCS , 1994, Adapt. Behav..

[28]  Chris Melhuish,et al.  ZCS and TCS learning classifier system controllers on real robots , 2002 .

[29]  J. Doyne Farmer,et al.  A Rosetta stone for connectionism , 1990 .

[30]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .