Abstract
This paper presents a behavioral ontogeny for artificial agents based on the interactive memorization of sensorimotor invariants. The agents are controlled by continuous timed recurrent neural networks (CTRNNs) which bind their sensors and motors within a dynamic system. The behavioral ontogenesis is based on a phylogenetic approach: memorization occurs during the agent’s lifetime and an evolutionary algorithm discovers CTRNN parameters. This shows that sensorimotor invariants can be durably modified through interaction with a guiding agent. After this phase has finished, agents are able to adopt new sensorimotor invariants relative to the environment with no further guidance. We obtained these kinds of behaviors for CTRNNs with 3–6 units, and this paper examines the functioning of those CTRNNs. For instance, they are able to internally simulate guidance when it is externally absent, in line with theories of simulation in neuroscience and the enactive field of cognitive science.
Similar content being viewed by others
References
Varela FJ, Thompson E, Rosch E (1991) The embodied mind: Cognitive science and human experience. MIT Press, Cambridge, MA
Shapiro L (2011) Travelling in style from standard cognitive science to embodied cognition. Constructivist 7(3):231–233
Noë A (2004) Action in perception. MIT Press, Cambridge
Smith L, Thenlen E (2003) Development as a dynamic system. Trends Cogn Sci 7(8):343–348
Warren WH (2006) The dynamics of perception and action. Psychol Rev 113(2):358–389
Beer RD (2000) Dynamical approaches to cognitive science. Trends Cogn Sci 4(3):91–99
Di Paolo E, Iizuka H (2008) How (not) to model autonomous behavior. Biosystems 91(2):409–423
Wood R, Di Paolo EA (2007) New models for old questions: evolutionary robotics and the ‘A not B’ error. In: Proceedings of the 9th European Conference on artificial life ECAL
Piaget J (1962) Play, dreams and imitation in childhood. Norton, New York
Tuci E, Quinn M, Harvey I (2002) An evolutionary ecological approach to the study of learning behavior using a robot-based model. Adapt Behav 10(3):201–221
Izquierdo E, Harvey I, Beer R (2008) Associative learning on a continuum in evolved dynamical neural network. Adapt Behav 16(6):361–384
Kugiumutzakis G (1999) Genesis and development of early infant mimesis to facial and vocal models. In: Nadel J, Butterworth G (eds) Imitation in infancy. Cambridge University Press, Cambridge, pp 36–59
Charles O, Tony P, St D (2012) With a little help from selection pressures: evolution of memory in robot controllers. Artif Life 13:407–414
Sutton R, Barto A (1998) Reinforcement learning. MIT Press, Cambridge
Harvey I (2011) The microbial genetic algorithm. In: Advances in artificial life. Darwin Meets von Neumann, pp 126–133
Mouret JB, Doncieux S (2009) Using behavioral exploration objectives to solve deceptive problems in neuro-evolution. In: Proceedings of the 11th Annual conference on genetic and evolutionary computation. GECCO’09, pp 627–634
De Loor P, Manac’h K, Tisseau J (2009) Enaction-based artificial intelligence: toward co-evolution with humans in the loop. Minds Mach 19(3):319–343
Raos Vassilis SHE, Evangeliou Mina N (2007) Mental simulation of action in the service of action perception. J Neurosci 27(46):12675–12683
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
De Loor, P., Manac’h, K. & Chevaillier, P. The memorization of in-line sensorimotor invariants: toward behavioral ontogeny and enactive agents. Artif Life Robotics 19, 127–135 (2014). https://doi.org/10.1007/s10015-014-0143-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-014-0143-3