{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:25:26Z","timestamp":1780637126445,"version":"3.54.1"},"reference-count":56,"publisher":"MIT Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Evolutionary Computation"],"published-print":{"date-parts":[[2012,3]]},"abstract":"<jats:p>Evolutionary robotics (ER) aims at automatically designing robots or controllers of robots without having to describe their inner workings. To reach this goal, ER researchers primarily employ phenotypes that can lead to an infinite number of robot behaviors and fitness functions that only reward the achievement of the task\u2014and not how to achieve it. These choices make ER particularly prone to premature convergence. To tackle this problem, several papers recently proposed to explicitly encourage the diversity of the robot behaviors, rather than the diversity of the genotypes as in classic evolutionary optimization. Such an approach avoids the need to compute distances between structures and the pitfalls of the noninjectivity of the phenotype\/behavior relation; however, it also introduces new questions: how to compare behavior? should this comparison be task specific? and what is the best way to encourage diversity in this context? In this paper, we review the main published approaches to behavioral diversity and benchmark them in a common framework. We compare each approach on three different tasks and two different genotypes. The results show that fostering behavioral diversity substantially improves the evolutionary process in the investigated experiments, regardless of genotype or task. Among the benchmarked approaches, multi-objective methods were the most efficient and the generic, Hamming-based, behavioral distance was at least as efficient as task specific behavioral metrics.<\/jats:p>","DOI":"10.1162\/evco_a_00048","type":"journal-article","created":{"date-parts":[[2011,8,12]],"date-time":"2011-08-12T18:40:13Z","timestamp":1313174413000},"page":"91-133","source":"Crossref","is-referenced-by-count":190,"title":["Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study"],"prefix":"10.1162","volume":"20","author":[{"given":"J.-B.","family":"Mouret","sequence":"first","affiliation":[{"name":"ISIR, Universit\u00e9 Pierre et Marie Curie-Paris 6, CNRS UMR 7222, Paris, F-75252, Paris Cedex 05, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Doncieux","sequence":"additional","affiliation":[{"name":"ISIR, Universit\u00e9 Pierre et Marie Curie-Paris 6, CNRS UMR 7222, Paris, F-75252, Paris Cedex 05, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36970-8_28"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1137\/0201008"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830657"},{"key":"B4","first-page":"11","author":"Birattari M.","year":"2002","journal-title":"GECCO\u201902: Proceedings of the 4th Annual Genetic and Evolutionary Computation Conference"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830504"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1557","DOI":"10.1145\/1068009.1068257","author":"Bui L.","year":"2005","journal-title":"GECCO\u201905: Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(97)00179-7"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61723-X_1004"},{"key":"B9","first-page":"11","author":"De Jong E. D.","year":"2001","journal-title":"GECCO\u201901: Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation"},{"key":"B10","volume-title":"Multi-objectives optimization using evolutionary algorithms","author":"Deb K.","year":"2001"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45356-3_83"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36605-9_57"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1570152"},{"key":"B14","first-page":"1303","author":"Doncieux S.","year":"2010","journal-title":"IEEE Congress on Evolutionary Computation (CEC)"},{"key":"B15","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-642-18272-3_1","volume-title":"New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob Workshop. Studies in Computational Intelligence","volume":"341","author":"Doncieux S.","year":"2009"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-007-0002-4"},{"key":"B18","doi-asserted-by":"crossref","first-page":"421","DOI":"10.7551\/mitpress\/3117.003.0061","author":"Floreano D.","year":"1994","journal-title":"From Animals to Animats 3: Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior (SAB\u201994)"},{"key":"B19","volume-title":"Artificial intelligence through simulated evolution","author":"Fogel L. G.","year":"1966"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1145\/1389095.1389276"},{"key":"B21","first-page":"74","volume-title":"Genetic algorithms and simulated annealing","author":"Goldberg D. E.","year":"1987"},{"key":"B22","first-page":"37","author":"Goldberg D. E.","year":"1992","journal-title":"Parallel Problem Solving from Nature, PPSN II"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569918"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1177\/105971239400300202"},{"key":"B25","doi-asserted-by":"crossref","first-page":"392","DOI":"10.7551\/mitpress\/3117.003.0058","author":"Harvey I.","year":"1994","journal-title":"From Animals to Animats 3: Proceedings of the Third International Conference on Simulation of Adaptive Behavior"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1090.001.0001"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1162\/106454602320991837"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44719-9_19"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1109\/72.712153"},{"key":"B30","first-page":"329","author":"Lehman J.","year":"2008","journal-title":"Proceedings of Artificial Life XI"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1201\/9781420037715.ch4"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1038\/35023115"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-003-0106-z"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1887\/0750308958\/b386c54"},{"key":"B36","first-page":"247","author":"Mauldin M.","year":"1984","journal-title":"Proceedings of the National Conference on Artificial Intelligence"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-64957-3_61"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830595"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-18272-3_10"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69134-1_21"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2009.4983077"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569988"},{"key":"B43","first-page":"4079","author":"Mouret J.-B.","year":"2010","journal-title":"IEEE Congress on Evolutionary Computation (CEC)"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1007\/11840541_50"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2889.001.0001"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569923"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1109\/4235.735432"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1007\/BF01876146"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2009.4982974"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1162\/106365603766646816"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1145\/1389095.1389147"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78761-7_17"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1177\/1059712303113003"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1570213"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(92)90136-J"}],"container-title":["Evolutionary Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/EVCO_a_00048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T22:12:35Z","timestamp":1712700755000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/evco\/article\/20\/1\/91-133\/920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,3]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,3]]}},"alternative-id":["10.1162\/EVCO_a_00048"],"URL":"https:\/\/doi.org\/10.1162\/evco_a_00048","relation":{},"ISSN":["1063-6560","1530-9304"],"issn-type":[{"value":"1063-6560","type":"print"},{"value":"1530-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,3]]}}}