{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/evolution-of-a-functionally-diverse-swarm-via","title":"Evolution of a Functionally Diverse Swarm via a Novel Decentralised Quality-Diversity Algorithm","arxiv_id":"1804.07655","date":"2018-04-20","proceeding":null,"authors":["Emma Hart","Andreas S. W. Steyven","Ben Paechter"],"abstract":"The presence of functional diversity within a group has been demonstrated to\nlead to greater robustness, higher performance and increased problem-solving\nability in a broad range of studies that includes insect groups, human groups\nand swarm robotics. Evolving group diversity however has proved challenging\nwithin Evolutionary Robotics, requiring reproductive isolation and careful\nattention to population size and selection mechanisms. To tackle this issue, we\nintroduce a novel, decentralised, variant of the MAP-Elites illumination\nalgorithm which is hybridised with a well-known distributed evolutionary\nalgorithm (mEDEA). The algorithm simultaneously evolves multiple diverse\nbehaviours for multiple robots, with respect to a simple token-gathering task.\nEach robot in the swarm maintains a local archive defined by two pre-specified\nfunctional traits which is shared with robots it come into contact with. We\ninvestigate four different strategies for sharing, exploiting and combining\nlocal archives and compare results to mEDEA. Experimental results show that in\ncontrast to previous claims, it is possible to evolve a functionally diverse\nswarm without geographical isolation, and that the new method outperforms mEDEA\nin terms of the diversity, coverage and precision of the evolved swarm.","url_abs":"http://arxiv.org/abs/1804.07655v1","url_pdf":"http://arxiv.org/pdf/1804.07655v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"evolution-of-a-functionally-diverse-swarm-via","repo_url":"https://github.com/asteyven/EDQD-GECCO2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}