Affiliation:
1. Institute of Cognitive Sciences and Technologies, National Research Council (CNR-ISTC). luca.simione@istc.cnr.it
2. Institute of Cognitive Sciences and Technologies, National Research Council (CNR-ISTC). stefano.nolfi@istc.cnr.it
3. Innopolis University
Abstract
Abstract
The possibility of using competitive evolutionary algorithms to generate long-term progress is normally prevented by the convergence on limit cycle dynamics in which the evolving agents keep progressing against their current competitors by periodically rediscovering solutions adopted previously. This leads to local but not to global progress (i.e., progress against all possible competitors). We propose a new competitive algorithm that produces long-term global progress by identifying and filtering out opportunistic variations, that is, variations leading to progress against current competitors and retrogression against other competitors. The efficacy of the method is validated on the coevolution of predator and prey robots, a classic problem that has been used in related researches. The accumulation of global progress over many generations leads to effective solutions that involve the production of articulated behaviors. The complexity of the behavior displayed by the evolving robots increases across generations, although progress in performance is not always accompanied by behavior complexification.
Subject
Artificial Intelligence,General Biochemistry, Genetics and Molecular Biology
Reference55 articles.
1. Angeline, P. J., & Pollack, J. B. (1993). Competitive environments evolve better solutions for complex tasks. In Proceedings of the 5th International Conference on Genetic Algorithms (pp. 264–270). DOI: https://dl.acm.org/doi/10.5555/645513.657590
2. Baldassarre, G., Trianni, V., Bonani, M., et al (2007). Self-organized coordinated motion in groups of physically connected robots. IEEE Transactions on Systems, Man, and Cybernetics, Part B, Cybernetics37, 224–239. DOI: https://doi.org/10.1109/TSMCB.2006.881299, PMID: 17278574
3. Bansal, T., Pachocki, J., Sidor, S., et al (2018). Emergent complexity via multi-agent competition. In 6th International Conference on Learning Representations, ICLR 2018—Conference Track Proceedings.
4. Bonani, M., Longchamp, V., Magnenat, S., et al (2010). The marXbot, a miniature mobile robot opening new perspectives for the collective-robotic research. In IEEE/RSJ 2010 International Conference on Intelligent Robots and Systems, IROS 2010—Conference Proceedings (pp. 4187–4193). New York: IEEE. DOI: https://doi.org/10.1109/IROS.2010.5649153
5. Buason, G., Bergfeldt, N., & Ziemke, T. (2005). Brains, bodies, and beyond: Competitive co-evolution of robot controllers, morphologies and environments. In Genetic Programming and Evolvable Machines, 6, 25–51. DOI: https://doi.org/10.1007/s10710-005-7618-x
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献