{"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/quality-diversity-through-surprise","title":"Quality Diversity Through Surprise","arxiv_id":"1807.02397","date":"2018-07-06","proceeding":null,"authors":["Daniele Gravina","Antonios Liapis","Georgios N. Yannakakis"],"abstract":"Quality diversity is a recent family of evolutionary search algorithms which\nfocus on finding several well-performing (quality) yet different (diversity)\nsolutions with the aim to maintain an appropriate balance between divergence\nand convergence during search. While quality diversity has already delivered\npromising results in complex problems, the capacity of divergent search\nvariants for quality diversity remains largely unexplored. Inspired by the\nnotion of surprise as an effective driver of divergent search and its\northogonal nature to novelty this paper investigates the impact of the former\nto quality diversity performance. For that purpose we introduce three new\nquality diversity algorithms which employ surprise as a diversity measure,\neither on its own or combined with novelty, and compare their performance\nagainst novelty search with local competition, the state of the art quality\ndiversity algorithm. The algorithms are tested in a robot navigation task\nacross 60 highly deceptive mazes. Our findings suggest that allowing surprise\nand novelty to operate synergistically for divergence and in combination with\nlocal competition leads to quality diversity algorithms of significantly higher\nefficiency, speed and robustness.","url_abs":"http://arxiv.org/abs/1807.02397v4","url_pdf":"http://arxiv.org/pdf/1807.02397v4.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":"quality-diversity-through-surprise","repo_url":"https://gitlab.com/2factor/QDSurprise","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"robot-navigation","task_name":"Robot Navigation"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}