ABSTRACT
We consider collective tasks to be solved by simple agents synthesized automatically by means of neuroevolution. We investigate whether driving neuroevolution by promoting a form of selfish behavior, i.e., by optimizing a fitness index that synthesizes the behavior of each agent independent of any other agent, may also result in optimizing global, system-wide properties. We focus on a specific and challenging task, i.e., evolutionary synthesis of agent as car controller for a road traffic scenario. Based on an extensive simulation-based analysis, our results indicate that even by optimizing the behavior of each single agent, the resulting system-wide performance is comparable to the performance resulting from optimizing the behavior of the system as a whole. Furthermore, agents evolved with a fitness promoting selfish behavior appear to lead to a system that is globally more robust with respect to the presence of unskilled agents.
- Eric Bonabeau. 2002. Agent-based modeling: Methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences 99, suppl 3 (2002), 7280--7287.Google ScholarCross Ref
- Manuele Brambilla, Eliseo Ferrante, Mauro Birattari, and Marco Dorigo. 2013. Swarm robotics: a review from the swarm engineering perspective. Swarm Intelligence 7, 1 (2013), 1--41.Google ScholarCross Ref
- Miguel C Figueiredo, Rosaldo JF Rossetti, Rodrigo AM Braga, and Luis Paulo Reis. 2009. An approach to simulate autonomous vehicles in urban traffic scenarios. In Intelligent Transportation Systems, 2009. ITSC'09. 12th International IEEE Conference on. IEEE, 1--6.Google ScholarCross Ref
- Robert L Goldstone and Marco A Janssen. 2005. Computational models of collective behavior. Trends in cognitive sciences 9, 9 (2005), 424--430.Google Scholar
- Tobias Holstein, Gordana Dodig-Crnkovic, and Patrizio Pelliccione. 2018. Ethical and Social Aspects of Self-Driving Cars. arXiv preprint arXiv:1802.04103 (2018).Google Scholar
- Ryan Lukeman, Yue-Xian Li, and Leah Edelstein-Keshet. 2010. Inferring individual rules from collective behavior. Proceedings of the National Academy of Sciences 107, 28 (2010), 12576--12580.Google ScholarCross Ref
- Eric Medvet, Alberto Bartoli, and Jacopo Talamini. 2017. Road Traffic Rules Synthesis Using Grammatical Evolution. In European Conference on the Applications of Evolutionary Computation. Springer, 173--188.Google Scholar
- Geoff S Nitschke, Martijn C Schut, and AE Eiben. 2010. Collective neuro-evolution for evolving specialized sensor resolutions in a multi-rover task. Evolutionary Intelligence 3, 1 (2010), 13--29.Google ScholarCross Ref
- Stefano Nolfi, Josh C Bongard, Phil Husbands, and Dario Floreano. 2016. Evolutionary Robotics.Google Scholar
- Liviu Panait and Sean Luke. 2005. Cooperative multi-agent learning: The state of the art. Autonomous agents and multi-agent systems 11, 3 (2005), 387--434. Google ScholarDigital Library
- Julia K Parrish and Leah Edelstein-Keshet. 1999. Complexity, pattern, and evolutionary trade-offs in animal aggregation. Science 284, 5411 (1999), 99--101.Google Scholar
- Kenneth O Stanley and Risto Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evolutionary computation 10, 2 (2002), 99--127. Google ScholarDigital Library
- Jekanthan Thangavelautham and Gabriele MT D'eleuterio. 2004. A neuroevolutionary approach to emergent task decomposition. In International Conference on Parallel Problem Solving from Nature. Springer, 991--1000.Google ScholarCross Ref
- DWF van Krevelen and Geoff S Nitschke. 2008. Neuro-evolution for a gathering and collective construction task. In Proceedings of the 10th annual conference on Genetic and evolutionary computation. ACM, 225--232. Google ScholarDigital Library
- Chern Han Yong and Risto Miikkulainen. 2001. Cooperative coevolution of multi-agent systems. University of Texas at Austin, Austin, TX (2001).Google Scholar
Index Terms
- Selfish vs. global behavior promotion in car controller evolution
Recommendations
Neuroevolution of an automobile crash warning system
GECCO '05: Proceedings of the 7th annual conference on Genetic and evolutionary computationMany serious automobile accidents could be avoided if drivers were warned of impending crashes before they occurred. In this paper, a vehicle warning system is evolved to predict such crashes in the RARS driving simulator. The NeuroEvolution of ...
An examination of different fitness and novelty based selection methods for the evolution of neural networks
It has been suggested recently that it is a reasonable abstraction of evolutionary processes to use evolutionary algorithms that select individuals based on the novelty of their behavior instead of their fitness. Here we study the performance of fitness-...
Sustaining behavioral diversity in NEAT
GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computationNiching schemes, which sustains population diversity and let an evolutionary population avoid premature convergence, have been extensively studied in the research field of evolutionary algorithms. Neuroevolutionary (NE) algorithms, such as NEAT, have ...
Comments