Abstract
This paper describes the simulated car racing competition that was arranged as part of the 2007 IEEE Congress on Evolutionary Computation. Both the game that was used as the domain for the competition, the controllers submitted as entries to the competition and its results are presented. With this paper, we hope to provide some insight into the efficacy of various computational intelligence methods on a well-defined game task, as well as an example of one way of running a competition. In the process, we provide a set of reference results for those who wish to use the simplerace game to benchmark their own algorithms. The paper is co-authored by the organizers and participants of the competition.
Similar content being viewed by others
References
M. Monster, Car physics for games. http://home.planet.nl/ monstrous/tutcar.html (2003)
D.M. Bourg, in Physics for Game Developers (O’Reilly, 2002)
K.O. Stanley, R. Miikkulainen, Competitive coevolution through evolutionary complexification. J. Artif. Intell. Res. 21, 63–100 (2004)
K.O. Stanley, Efficient evolution of neural networks through complexification. PhD thesis, Department of Computer Sciences, University of Texas, Austin, TX (2004)
J. Togelius, P. Burrow, S.M. Lucas, Multi-population competitive co-evolution of car racing controllers. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC) (IEEE Press, 2007), pp. 4043–4050
T. Miconi, A. Channon, The n-strikes-out algorithm: a steady-state algorithm for coevolution. in Proceedings of the IEEE Congress on Evolutionary Computation (CEC) (IEEE Press, 2006), pp. 1639–1646
F. Gomez, R. Miikkulainen, Incremental evolution of complex general behavior. Adapt. Behav. 5, 317–342 (1997)
R.D. Beer, On the dynamics of small continuous-time recurrent neural networks. Adapt. Behav. 3, 471–511 (1995)
F. Gomez, J. Schmidhuber, R. Miikkulainen, Efficient non-linear control through neuroevolution. In Proceedings of the European Conference on Machine Learning (ECML), ed. by J. Fürnkranz, T. Scheffer, M. Spiliopoulu (2006), pp. 654–662
R.M. MacCallum, Introducing a Perl genetic programming system: and can meta-evolution solve the bloat problem. In Genetic Programming, Proceedings of EuroGP’2003. Volume 2610 of LNCS, 14–16 April 2003, ed. by C. Ryan, T. Soule, M. Keijzer, E. Tsang, R. Poli, E. Costa (Springer-Verlag, Essex, 2003), pp. 364–373
R.M. MacCallum, The Open Source Perl Genetic Programming System. http://perlgp.org (2003)
R.S. Sutton, A.G. Barto, in Reinforcement Learning: An Introduction (MIT Press, Cambridge, MA, 1998)
D.T. Ho, J.M. Garibaldi, A novel fuzzy inferencing methodology for simulated car racing. In To be Published in the Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (IEEE Press, 2008)
J. Togelius, S.M. Lucas, R. De Nardi, Computational intelligence in racing games. in Advanced Intelligent Paradigms in Computer Games, ed. by N. Baba, L.C. Jain, H. Handa (Springer, 2007)
J. Togelius, Optimization, imitation and innovation: computational intelligence and games. PhD thesis, Department of Computing and Electronic Systems, University of Essex, Colchester, UK, 2007
I. Tanev, M. Joachimczak, H. Hemmi, K. Shimohara, Evolution of the driving styles of anticipatory agent remotely operating a scaled model of racing car. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC) (IEEE Press, 2005), pp. 1891–1898
J. Togelius, R. De Nardi, H. Marques, R. Newcombe, S.M. Lucas, O. Holland, Nonlinear dynamics modelling for controller evolution. In Proceedings of the Genetic and Evolutionary Computing Conference (GECCO) (ACM Press, London, UK, 2007)
S. Whiteson, A. White, R. Sutton, D. Precup, P. Stone, M. Littman, N. Vlassos, M. Riedmiller, Rl competition. http://rl-competition.org (2008)
Acknowledgements
Thanks to anonymous reviewers for a number of helpful comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Togelius, J., Lucas, S., Thang, H.D. et al. The 2007 IEEE CEC simulated car racing competition. Genet Program Evolvable Mach 9, 295–329 (2008). https://doi.org/10.1007/s10710-008-9063-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10710-008-9063-0