Abstract
Learning classifier systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena. This paper presents an explicitly cognitive LCS by using spiking neural networks as classifiers, providing each classifier with a measure of temporal dynamism. We employ a constructivist model of growth of both neurons and synaptic connections, which permits a genetic algorithm to automatically evolve sufficiently-complex neural structures. The spiking classifiers are coupled with a temporally-sensitive reinforcement learning algorithm, which allows the system to perform temporal state decomposition by appropriately rewarding “macro-actions”, created by chaining together multiple atomic actions. The combination of temporal reinforcement learning and neural information processing is shown to outperform benchmark neural classifier systems, and successfully solve a robotic navigation task.
Similar content being viewed by others
References
Beer RD (1995) On the dynamics of small continuous-time recurrent neural networks. Adapt Behav 3:469–509. doi:10.1177/105971239500300405
Bonarini A (1998) Reinforcement distribution to fuzzy classifiers. In: Proceedings of the IEEE world congress on computational intelligence (WCCI)—evolutionary computation, IEEE Computer Press, pp 51–56
Boyan JA, Moore AW (1995) Generalization in reinforcement learning: safely approximating the value function. In: Tesauro G, Touretzky DS, Leen TK (eds) Advances in neural information processing systems 7. The MIT Press, Cambridge, pp 369–376
Bull L (2002) On using constructivism in neural classifier systems. In: Merelo J, Adamidis P, Beyer HG, Fernandez-Villacanas JL, Schwefel HP (eds) Parallel problem solving from nature—PPSN VII. Springer, New York, pp 558–567
Bull L, Hurst J (2003) A neural learning classifier system with self-adaptive constructivism. In: Proceedings of the IEEE congress on evolutionary computation, IEEE Press, pp 991–997
Butz MV, Herbort O (2008) Context-dependent predictions and cognitive arm control with XCSF. In: Ryan C, Keijzer M (eds) Proceedings of the genetic and evolutionary computation conference, GECCO 2008, ACM, Atlanta, 12–16 July 2008, pp 1357–1364
Butz MV, Lanzi PL, Wilson SW (2006) Hyper-ellipsoidal conditions in xcs: rotation, linear approximation, and solution structure. In: Proceedings of the 8th annual conference on genetic and evolutionary computation (GECCO ’06), ACM Press, New York, pp 1457–1464. doi:10.1145/1143997.1144237
Buzsaki G (2006) Rhythms of the brain. Oxford University Press, Oxford
Cazangi RR, Zuben FJV, Figueiredo M (2003) A classifier system in real applications for robot navigation. In: Proceedings of the IEEE congress on evolutionary computation, IEEE, pp 574–580
Churchill AW, Fernando C (2014) An evolutionary cognitive architecture made of a bag of networks. Evol Intell 7(3):169–182
Donnart JY, Meyer JA (1996) Learning reactive and planning rules in a motivationally autonomous animat. IEEE Trans Syst Man Cybern 26(3):381–395
Dorigo M, Colombetti M (1994) Robot shaping: developing autonomous agents through learning. Artif Intell 71(2):321–370
Fauer S, Schwenker F (2015) Neural network ensembles in reinforcement learning. Neural Process Lett 41(1):55–69. doi:10.1007/s11063-013-9334-5
Fernando C (2011) Symbol manipulation and rule learning in spiking neuronal networks. J theor biol 275(1):29–41
Fernando C, Goldstein R, Szathmáry E (2010) The neuronal replicator hypothesis. Neural Comput 22(11):2809–2857
Floreano D, Mattiussi C (2001) Evolution of spiking neural controllers for autonomous vision-based robots. Lect Notes Comput Sci 2217:38–61
Floreano D, Schoeni N, Caprari G, Blynel J (2002) Evolutionary bitsnspikes. In: Proceedings of the eight international conference on artificial life, MIT Press
Gerstner W, Kistler W (2002) Spiking neuron models—single neurons, populations, plasticity. Cambridge University Press, Cambridge
Hagras H, Sobh T (2002) Intelligent learning and control of autonomous robotic agents operating in unstructured environments. Inf Sci 145(1):1–12
He P, Jagannathan S (2007) Reinforcement learning neural-network-based controller for nonlinear discrete-time systems with input constraints. In: Proceedings of the IEEE transactions on systems, man, and cybernetics, Part B: cybernetics, 37(2):425–436
Hodgkin AL, Huxley AF (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117(4):500
Holland JH (1975) Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor
Holland JH (1976) Adaptation. In: Rosen R, Snell F (eds) Progress in theoretical biology. Academic Press, New York
Holland JH, Reitman JS (1978) Cognitive systems based on adaptive algorithms. In: Waterman DA, Hayes-Roth F (eds) Pattern-directed inference systems. Academic Press, Orlando, pp 313–329
Howard G, Bull L, Lanzi PL (2010) A spiking neural representation for xcsf. In: Proceedings of the IEEE congress on evolutionary computation (CEC), IEEE, pp 1–8
Howard GD, Bull L (2008) On the effects of node duplication and connection-oriented constructivism in neural XCSF. In: Ryan C, Keijzer M (eds) In: Proceedings of the genetic and evolutionary computation conference, GECCO 2008, Atlanta, Companion Material, ACM, 12–16 July 2008, pp 1977–1984
Howard GD, Bull L, Lanzi PL (2009) Towards continuous actions in continuous space and time using self-adaptive constructivism in neural XCSF. In: Proceedings of the 11th annual conference on genetic and evolutionary computation, GECCO ’09, ACM, New York, pp 1219–1226. doi:10.1145/1569901.1570065
Hurst J, Bull L (2006) A neural learning classifier system with self-adaptive constructivism for mobile robot control. Artif Life 12(3):353–380
Hurst J, Bull L, Melhuish C (2002) TCS learning classifier system controller on a real robot. Lect Notes Comput Sci 2439:588–600
Kistler WM (2002) Spike-timing dependent synaptic plasticity: a phenomenological framework. Biol Cybern 87(5–6):416–427. doi:10.1007/s00422-002-0359-5
Lanzi P, Loiacono D (2006) Xcsf with neural prediction. In: Yen GG, Lucas SM, Fogel G, Kendall G, Salomon R, Zhang BT, Coello CAC, Runarsson TP (eds) Proceedings of the 2006 IEEE congress on evolutionary computation, IEEE Press, Vancouver, Canada, pp 2270–2276. URL http://ieeexplore.ieee.org/servlet/opac?punumber=11108
Lanzi PL, Loiacono D, Wilson SW, Goldberg DE (2005) XCS with computed prediction in continuous multistep environments. In: Proceedings of the IEEE congress on evolutionary computation, IEEE, pp 2032–2039
Lanzi PL, Loiacono D, Wilson SW, Goldberg DE (2006) Classifier prediction based on tile coding. In: Proceedings of the 8th annual conference on genetic and evolutionary computation, GECCO ’06, ACM, New York, pp 1497–1504
Maass W (1997) Networks of spiking neurons: the third generation of neural network models. Neural Netw 10(9):1659–1671
Michel O (2004) WebotsTM: professional mobile robot simulation. Int J Adv Robot Syst 1(1):39–42
Moioli RC, Vargas PA, Zuben FJV (2007) Analysing learning classifier systems in reactive and non-reactive robotic tasks. In: Bacardit J, Bernadó-Mansilla E, Butz MV, Kovacs T, Llorà X, Takadama K (eds) International workshop on learning classifier systems IWLCS, lecture notes in computer science, Springer, New York, vol 4998, pp 286–305
Pipe AG, Carse B (2002) First results from experiments in fuzzy classifier system architectures for mobile robotics. Lect Notes Comput Sci 2439:578–587
Preen R, Bull L (2014) Discrete and fuzzy dynamical genetic programming in the xcsf learning classifier system. Soft Comput 18(1):153–167. doi:10.1007/s00500-013-1044-4
Quartz SR, Sejnowski TJ (1997) The neural basis of cognitive development: a constructivist manifesto. Behav Brain Sci 20(04):537–556
Rechenberg I (1973) Evolutionsstrategie: optimierung technischer systeme nach prinzipien der biologischen evolution. Frommann-Holzboog, Stuttgart
Rumelhart D, McClelland J (1986) Parallel distributed processing, vol 1 & 2. MIT Press, Cambridge
Schultz W (1998) Predictive reward signal of dopamine neurons. J Neurophysiol 80(1):1–27
Shouval H, Gavornik J (2011) A single spiking neuron that can represent interval timing: analysis, plasticity and multi-stability. J Comput Neurosci 30(2):489–499
Stolzmann W (1999) Latent learning in khepera robots with anticipatory classifier systems. In: Lanzi PL, Stolzmann W, Wilson SW (eds) 2nd international workshop on learning classifier systems. Orlando, pp 290–297
Studley M, Bull L (2005) X-TCS: accuracy-based learning classifier system robotics. In: Proceedings of the IEEE congress on evolutionary computation, IEEE, pp 2099–2106
Sutton RS (1996) Generalization in reinforcement learning: successful examples using sparse coarse coding. In: Touretzky DS, Mozer MC, Hasselmo ME (eds) Advances in neural information processing systems 8. MIT Press, Cambridge, pp 1038–1044
Sutton RS, Precup D, Singh S (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1–2):181–211
Watkins C (1989) Learning from delayed rewards. PhD thesis, Cambridge University, Psychology Department, Cambridge
Webb A, Hart E, Ross P, Lawson A (2003) Controlling a simulated khepera with an XCS classifier system with memory. In: Banzhaf W, Christaller T, Dittrich P, Kim JT, Ziegler J (eds) Proceedings of the advances in artificial life, 7th European conference, ECAL 2003, lecture notes in computer science, vol 2801, Springer, Dortmund, pp 885–892, 14–17 Sept 2003
Wilson SW (2000) Get real! xcs with continuous-valued inputs. In: Lanzi PL, Stolzmann W, Wilson SW (eds) Learning classifier systems, from foundations to applications, LNAI-1813. Springer, New York, pp 209–219
Wilson SW (2001) Function approximation with a classifier system. In: Spector L, Goodman ED, Wu A, Langdon WB, Voigt HM, Gen M, Sen S, Dorigo M, Pezeshk S, Garzon MH, Burke E (eds) Proceedings of the genetic and evolutionary computation conference (GECCO-2001). Morgan Kaufmann, San Francisco, pp 974–981
Wilson SW (2001b) Mining oblique data with XCS. In: Lanzi PL, Stolzmann W, Wilson SW (eds) Advances in learning classifier systems, third international workshop, IWLCS 2000, LNCS, vol 1996, Springer, Heidelberg, pp 158–176
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Howard, D., Bull, L. & Lanzi, PL. A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers. Neural Process Lett 44, 125–147 (2016). https://doi.org/10.1007/s11063-015-9451-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-015-9451-4