Abstract
Artificial agents controlled by dynamic recurrent node networks with fixed weights are evolved to search for food and associate it with one of two different temperatures depending on experience. The task requires either instrumental or classical conditioned responses to be learned. The paper extends previous work in this area by requiring that a situated agent be capable of re-learning during its lifetime. We analyse the best-evolved agent’s behaviour and explain in some depth how it arises from the dynamics of the coupled agent-environment system.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Beer, R.D.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4), 469–509 (1995)
Blynel, J., Floreano, D.: Levels of dynamics and adaptive behavior in evolutionary neural controllers. In: Proc. of the 7th Int. Conf. on Simulation of Adaptive Behavior: From animals to animats, pp. 272–281. MIT Press, Cambridge (2002)
Fernando, C.: A situated and embodied model of classical and instrumental learning. Master’s thesis, COGS, University of Sussex (2002)
Harvey, I.: Artificial evolution: a continuing SAGA. In: Gomi, T. (ed.) Evolutionary Robotics. From Intelligent Robotics to Artificial Life. LNCS, vol. 2217, Springer, Heidelberg (2001)
Hedgecock, E.M., Russell, R.L.: Normal and mutant thermotaxis in the nematode caenorhabditis elegans. Proc. Nat. Acad. Sci. USA 72(10), 4061–4065 (1975)
Phattanasri, P., Chiel, H.J., Beer, R.D.: The dynamics of associative learning in evolved model circuits. Adaptive Behavior (Submitted)
Tuci, E., Quinn, M., Harvey, I.: An evolutionary ecological approach to evolving learning behavior using a robot based model. Adaptive Behavior 10(3/4), 201–221 (2003)
Yamauchi, B.M., Beer, R.D.: Integrating reactive, sequential and learning behavior using dynamical neural networks. In: Cliff, D., Husbands, P., Meyer, J., Wilson, S. (eds.) From Animals to Animats 3: Proc. of the Third Int. Conf. on Simulation of Adaptive Behavior, pp. 382–391. MIT Press, Cambridge (1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Izquierdo, E., Harvey, I. (2007). The Dynamics of Associative Learning in an Evolved Situated Agent. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds) Advances in Artificial Life. ECAL 2007. Lecture Notes in Computer Science(), vol 4648. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74913-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-540-74913-4_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74912-7
Online ISBN: 978-3-540-74913-4
eBook Packages: Computer ScienceComputer Science (R0)