The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Encouraging Behavioral Diversity in Evolutionary Robotics: An Empirical Study
Abstract
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—and 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A fast and elitist multiobjective genetic algorithm: NSGA-II
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.996017 · Cited by 50,053
Holland, J. H. (1992) · The MIT Press eBooks · doi:10.7551/mitpress/1090.001.0001 · Cited by 47,002
Multi-Objective Optimization Using Evolutionary Algorithms
Deb, K., & Kalyanmoy, D. (2001) · Andalas University Repository (Andalas University) · Cited by 14,918
A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimization: NSGA-II
Deb, K., Agrawal, S., Pratap, A., & Meyarivan, T. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45356-3_83 · Cited by 5,289
Evolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,258
Artificial Intelligence through Simulated Evolution
Fogel, L. J., Owens, A. J., & Walsh, M. J. (1966) · International Linear Collider · Cited by 2,796
Learning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 1×
“Elman-Jordan networks 3 (Elman, 1993) are simple recurrent neural networks that extend the multi-layer perceptron with a hidden layer of context units (figure 3).”
Genetic Algorithms and Simulated Annealing
Davis, L. D. (1987) · Cited by 1,759
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Nolfi, S., & Floreano, D. (2000) · The MIT Press eBooks · doi:10.7551/mitpress/2889.001.0001 · Cited by 1,513
Abandoning Objectives: Evolution Through the Search for Novelty Alone
Lehman, J., & Stanley, K. O. (2011) · Evolutionary Computation · doi:10.1162/evco_a_00025 · Cited by 917
Automatic design and manufacture of robotic lifeforms
Lipson, H., & Pollack, J. B. (2000) · Nature · doi:10.1038/35023115 · Cited by 883
A graph distance metric based on the maximal common subgraph
Bunke, H., & Shearer, K. (1998) · Pattern Recognition Letters · doi:10.1016/s0167-8655(97)00179-7 · Cited by 754
Neuroevolution: from architectures to learning
Floreano, D., Dürr, P., & Mattiussi, C. (2008) · Evolutionary Intelligence · doi:10.1007/s12065-007-0002-4 · Cited by 734
The Transitive Reduction of a Directed Graph
Aho, A. V., Garey, M. R., & Ullman, J. D. (1972) · SIAM Journal on Computing · doi:10.1137/0201008 · Cited by 718
Fitness sharing and niching methods revisited
Sareni, B., & Krahenbuhl, L. (1998) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.735432 · Cited by 578
A Racing Algorithm for Configuring Metaheuristics
Birattari, M., Stützle, T., Paquete, L., & Varrentrapp, K. (2002) · Cited by 498
2011 IEEE Congress of Evolutionary Computation (CEC)
(2011) · doi:10.1109/cec15497.2011 · Cited by 487
Exploiting Open-Endedness to Solve Problems Through the Search for Novelty
Lehman, J., & Stanley, K. O. (2008) · Cited by 408
On the editing distance between unordered labeled trees
Zhang, K., Statman, R., & Shasha, D. E. (1992) · Information Processing Letters · doi:10.1016/0020-0190(92)90136-j · Cited by 359
Reducing Local Optima in Single-Objective Problems by Multi-objectivization
Knowles, J. D., Watson, R. A. R., & Corne, D. (2001) · Lecture notes in computer science · doi:10.1007/3-540-44719-9_19 · Cited by 345
Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural-Network Driven Robot
Floreano, D., & Francesco Mondada, C. (1994) · The MIT Press eBooks · doi:10.7551/mitpress/3117.003.0061 · Cited by 333
Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural Network Driven Robot
Floreano, D., & Francesco Mondada, C. (1994) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-a-010111549 · Cited by 303
Simple Genetic Algorithms and the Minimal, Deceptive Problem
Goldberg, D. E. (1987) · Medical Entomology and Zoology · Cited by 297
Automatic Definition of Modular Neural Networks
Gruau, F. (1994) · Adaptive Behavior · doi:10.1177/105971239400300202 · Cited by 269
Seeing The Light: Artificial Evolution, Real Vision
Harvey, I., Husbands, P., & Cliff, D. (1994) · From Animals to Animats 3 · doi:10.7551/mitpress/3117.003.0058 · Cited by 225
Creating High-Level Components with a Generative Representation for Body-Brain Evolution
Hornby, G. S., & Pollack, J. B. (2002) · Artificial Life · doi:10.1162/106454602320991837 · Cited by 225
Reducing bloat and promoting diversity using multi-objective methods
de Jong, E. D., Watson, R. A. R., & Pollack, J. B. (2001) · Cited by 204
Kodjabachian, J., & Meyer, J.-A. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.712153 · Cited by 147
Novelty-Based Multiobjectivization
Mouret, J.-B. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-18272-3_10 · Cited by 139
Self-citationEvolution of swarm robotics systems with novelty search
Gomes, J., Urbano, P., & Christensen, A. L. (2013) · Swarm Intelligence · doi:10.1007/s11721-013-0081-z · Cited by 124
Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity
Mouret, J.-B., & Doncieux, S. (2009) · 2009 IEEE Congress on Evolutionary Computation · doi:10.1109/cec.2009.4983077 · Cited by 106
Self-citationParsons, S. (2004) · The Knowledge Engineering Review · doi:10.1017/s0269888905230357 · Cited by 87
Sustaining diversity using behavioral information distance
Gomez, F. J. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1569918 · Cited by 83
How novelty search escapes the deceptive trap of learning to learn
Risi, S., Vanderbleek, S. D., Hughes, C. E., & Stanley, K. O. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1569923 · Cited by 81
Schwefel, H. (1984) · Annals of Operations Research · doi:10.1007/bf01876146 · Cited by 72
Using multi-objective evolutionary algorithms for single-objective optimization
Segura, C., Coello, C. A. C., Miranda, G., & León, C. (2013) · 4OR · doi:10.1007/s10288-013-0248-x · Cited by 72
Sferesv2: Evolvin' in the multi-core world
Mouret, J.-B., & Doncieux, S. (2010) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2010.5586158 · Cited by 68
Self-citationUsing behavioral exploration objectives to solve deceptive problems in neuro-evolution
Mouret, J.-B., & Doncieux, S. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1569988 · Cited by 67
Self-citationSearching under Multi-evolutionary Pressures
Abbass, H. A., & Deb, K. (2003) · Lecture notes in computer science · doi:10.1007/3-540-36970-8_28 · Cited by 64
Behavioral diversity measures for Evolutionary Robotics
Doncieux, S., & Mouret, J.-B. (2010) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2010.5586100 · Cited by 62
Self-citationEvolutionary robotics: A survey of applications and problems
Meyer, J.-A., Husbands, P., & Harvey, I. R. (1998) · Lecture notes in computer science · doi:10.1007/3-540-64957-3_61 · Cited by 59
Evolving Controllers for Real Robots: A Survey of the Literature
Walker, J. H., Garrett, S. M., & Wilson, M. (2003) · Adaptive Behavior · doi:10.1177/1059712303113003 · Cited by 58
New Horizons in Evolutionary Robotics: Extended Contributions from the 2009 EvoDeRob Workshop
Doncieux, S., Bredèche, N., & Mouret, J.-B. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-18272-3 · Cited by 56
Self-citationEvolutionary Robotics: Exploring New Horizons
Doncieux, S., Mouret, J.-B., Bredèche, N., & Padois, V. (2011) · Studies in computational intelligence · doi:10.1007/978-3-642-18272-3_1 · Cited by 52
Self-citationIncremental Evolution of Animats’ Behaviors as a Multi-objective Optimization
Mouret, J.-B., & Doncieux, S. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-69134-1_21 · Cited by 52
Self-citationEvolutionary Robotics and Open-Ended Design Automation
Lipson, H. (2005) · doi:10.1201/9781420037715-9 · Cited by 42
Incremental Evolution of Target-Following Neuro-controllers for Flapping-Wing Animats
Mouret, J.-B., Doncieux, S., & Meyer, J.-A. (2006) · Lecture notes in computer science · doi:10.1007/11840541_50 · Cited by 37
Self-citationEvolutionary Robotics and Open-Ended Design Automation
Lipson, H. (2005) · CRC Press eBooks · doi:10.1201/9781420037715.ch4 · Cited by 26
Discovering Several Robot Behaviors through Speciation
Trujillo, L., Gustavo Olague, A., Lutton, É., & de Vega, F. F. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-78761-7_17 · Cited by 25
Guarding against premature convergence while accelerating evolutionary search
Bongard, J., & Hornby, G. S. (2010) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1830483.1830504 · Cited by 19
Generation of Diversity in a Reaction-Diffusion-Based Controller
Zahadat, P., & Schmickl, T. (2014) · Artificial Life · doi:10.1162/artl_a_00134 · Cited by 16
Sustaining behavioral diversity in NEAT
Moriguchi, H., & Honiden, S. (2010) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1830483.1830595 · Cited by 13
Behavior-based speciation for evolutionary robotics
Trujillo, L., Gustavo Olague, A., Lutton, É., & de Vega, F. F. (2008) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1389095.1389147 · Cited by 8
Toward Nonlinear Local Reinforcement Learning Rules Through Neuroevolution
Vassiliades, V., & Christodoulou, C. C. (2013) · Neural Computation · doi:10.1162/neco_a_00514 · Cited by 6
Cited by
Abandoning Objectives: Evolution Through the Search for Novelty Alone
Lehman, J., & Stanley, K. O. (2011) · Evolutionary Computation · doi:10.1162/evco_a_00025 · Cited by 917
Designing neural networks through neuroevolution
Stanley, K. O., Clune, J., Lehman, J., & Miikkulainen, R. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0006-z · Cited by 689
Exploration in deep reinforcement learning: A survey
Ladosz, P., Weng, L., Kim, M., & Oh, H. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.03.003 · Cited by 525
“More detailed reviews of exploration in evolution strategies can be found in [78] and [79].”
BackgroundQuality Diversity: A New Frontier for Evolutionary Computation
Pugh, J. K., Soros, L. B., & Stanley, K. O. (2016) · Frontiers in Robotics and AI · doi:10.3389/frobt.2016.00040 · Cited by 514
Illuminating search spaces by mapping elites
Mouret, J.-B., & Clune, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.04909 · Cited by 386
Self-citation
Metadata
- Authors
- Mouret, J.-B., & Doncieux, S.
- Venue
- Evolutionary Computation
- Publisher
- MIT Press
- Published
- 2012-03
- Volume
- 20
- Issue
- 1
- Pages
- 91-133
- ISSN
- 1063-6560 (ISSN-L)
- 1530-9304
- OpenAlex
- W2155921792
- Cited by
- 257
- References
- 54
- FWCI
- 18.33
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.