Abstract
An imitation game for learning action categories is proposed. It serves to invent and share a repertoire of action categories in a population of robotic agents. The agents start without any action categories built in, but they learn by imitating other agents and gradually invent categories for the actions they observe and execute. In other words, no action categories need to be defined beforehand, nor do agents have to be assigned fixed roles. If the population only consists of two agents, the repertoire of action categories can be learnt without feedback about the outcome of the game between both agents.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vogt, P.: Grounding language about actions: Mobile robots playing follow me games. In: Meyer, P., Bertholz, S., Floreano, F., Roitblat, H., Wilson, P. (eds.) SAB2000 Proceedings Supplement Book, International Society for Adaptive Behavior (2000)
Billard, A., Schaal, S.: Robust learning of arm trajectories through human demonstration. In: Proceedings of the International Conference on Intelligent and Robotics Systems, Hawaii, November 2001, pp. 82–90. IEEE Computer Society, Los Alamitos (2001)
Billard, A., Hayes, G.: Transmitting communication skills through imitation in autonomous robots. In: Birk, A., Demiris, J. (eds.) EWLR 1997. LNCS (LNAI), vol. 1545, pp. 79–95. Springer, Heidelberg (1998)
Alissandrakis, A., Nehaniv, C.L., Dautenhahn, K.: Do as I do: Correspondences across different robotic embodiments. In: Polani, D., Kim, J., Martinetz, T. (eds.) Proceedings of the Fifth German Workshop on Artificial Life (GWAL5), Lübeck, Germany, March 18-20, pp. 143–152 (2002)
de Boer, B.: Self organization in vowel systems. Journal of Phonetics 28, 441–465 (2000)
Belpaeme, T.: Factors influencing the origins of colour categories. PhD thesis, Artificial Intelligence Lab, Vrije Universiteit Brussel (2002)
Belpaeme, T., Steels, L., Van Looveren, J.: The construction and acquisition of visual categories. In: Birk, A., Demiris, J. (eds.) EWLR 1997. LNCS (LNAI), vol. 1545, pp. 1–12. Springer, Heidelberg (1998)
Jansen, B., de Vylder, B., de Boer, B., Belpaeme, T.: Emerging shared action categories in robotic agents through imitation. In: Dautenhahn, K., Nehaniv, C.L. (eds.) Proceedings of the Second International Symposium on Imitation in Animals and Artifacts, pp. 145–152. University of Wales, Aberystwyth (2003)
De Vylder, B.: Forward and inverse kinematics of the teach-robot. Technical Report AI MEMO 02-02, Artificial Intelligence Lab, Vrije Universiteit Brussel, Brussels (2002)
Myers, C.S., Rabiner, L.R.: A comparative study of several dynamic time-warping algorithms for connected word recognition. The Bell System Technical Journal 60, 1389–1409 (1981)
Corradini, A.: Dynamic time warping for off-line recognition of a small gesture vocabulary. In: IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS 2001), Vancouver, B.C., Canada, July 13–August 13, pp. 82–90. IEEE Computer Society, Los Alamitos (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jansen, B. (2003). An Imitation Game for Emerging Action Categories. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds) Advances in Artificial Life. ECAL 2003. Lecture Notes in Computer Science(), vol 2801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39432-7_86
Download citation
DOI: https://doi.org/10.1007/978-3-540-39432-7_86
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20057-4
Online ISBN: 978-3-540-39432-7
eBook Packages: Springer Book Archive