All Outputs (177)

Evolving Herding Behaviour Diversity in Robot Swarms (2023)
Presentation / Conference Contribution
Nitschke, G., Hallauer, S., & Hart, E. (2023, July). Evolving Herding Behaviour Diversity in Robot Swarms. Presented at Proceedings of the Companion Conference on Genetic and Evolutionary Computation, Lisbon, Portugal

Behavioural diversity has been demonstrated as beneficial in biological social systems, such as insect colonies and human societies, as well as artificial systems such as large-scale software and swarm-robotics systems. Evolutionary swarm robotics is... Read More about Evolving Herding Behaviour Diversity in Robot Swarms.

Towards optimisers that `Keep Learning' (2023)
Presentation / Conference Contribution
Hart, E., Miguel, I., Stone, C., & Renau, Q. (2023, July). Towards optimisers that `Keep Learning'. Presented at Companion Conference on Genetic and Evolutionary Computation, Lisbon, Portugal

We consider optimisation in the context of the need to apply an optimiser to a continual stream of instances from one or more domains, and consider how such a system might 'keep learning': by drawing on past experience to improve performance and lear... Read More about Towards optimisers that `Keep Learning'.

Learning-Based Neural Ant Colony Optimization (2023)
Presentation / Conference Contribution
Liu, Y., Qiu, J., Hart, E., Yu, Y., Gan, Z., & Li, W. (2023). Learning-Based Neural Ant Colony Optimization. In GECCO 2023: Proceedings of the Genetic and Evolutionary Computation Conference (47-55). https://doi.org/10.1145/3583131.3590483

In this paper, we propose a new ant colony optimization algorithm , called learning-based neural ant colony optimization (LN-ACO), which incorporates an "intelligent ant". This intelligent ant contains a convolutional neural network pre-trained on a... Read More about Learning-Based Neural Ant Colony Optimization.

Generating diverse and discriminatory knapsack instances by searching for novelty in variable dimensions of feature-space (2023)
Presentation / Conference Contribution
Marrero, A., Segredo, E., Hart, E., Bossek, J., & Neumann, A. (2023, July). Generating diverse and discriminatory knapsack instances by searching for novelty in variable dimensions of feature-space. Presented at GECCO 2023, Lisbon, Portugal

Generating new instances via evolutionary methods is commonly used to create new benchmarking data-sets, with a focus on attempting to cover an instance-space as completely as possible. Recent approaches have exploited Quality-Diversity methods to ev... Read More about Generating diverse and discriminatory knapsack instances by searching for novelty in variable dimensions of feature-space.

To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features (2023)
Presentation / Conference Contribution
Vermetten, D., Wang, H., Sim, K., & Hart, E. (2023, April). To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features. Presented at Evo Applications 2023, Brno, Czech Republic

Dynamic algorithm selection aims to exploit the complementarity of multiple optimization algorithms by switching between them during the search. While these kinds of dynamic algorithms have been shown to have potential to outperform their component a... Read More about To Switch or not to Switch: Predicting the Benefit of Switching between Algorithms based on Trajectory Features.

A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms (2023)
Presentation / Conference Contribution
Montague, K., Hart, E., Paechter, B., & Nitschke, G. (2023, April). A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms. Presented at EVOStar 2023, Brno, Czechia

Designing controllers for a swarm of robots such that collabo-rative behaviour emerges at the swarm level is known to be challenging. Evolutionary approaches have proved promising, with attention turning more recently to evolving repertoires of dive... Read More about A Quality-Diversity Approach to Evolving a Repertoire of Diverse Behaviour-Trees in Robot Swarms.

Improving the size and quality of MAP-Elites containers via multiple emitters and decoders for urban logistics (2023)
Presentation / Conference Contribution
Urquhart, N., & Hart, E. (2023, April). Improving the size and quality of MAP-Elites containers via multiple emitters and decoders for urban logistics. Presented at Evo Applications 2023, Brno, Czech Republic

Quality-diversity (QD) methods such as MAP-Elites have been demonstrated to be useful in the domain of combinatorial optimisation due to their ability to generate a large set of solutions to a single-objective problem that are diverse with respect to... Read More about Improving the size and quality of MAP-Elites containers via multiple emitters and decoders for urban logistics.

DIGNEA: A tool to generate diverse and discriminatory instance suites for optimisation domains (2023)
Journal Article
Marrero, A., Segredo, E., León, C., & Hart, E. (2023). DIGNEA: A tool to generate diverse and discriminatory instance suites for optimisation domains. SoftwareX, 22, Article 101355. https://doi.org/10.1016/j.softx.2023.101355

To advance research in the development of optimisation algorithms, it is crucial to have access to large test-beds of diverse and discriminatory instances from a domain that can highlight strengths and weaknesses of different algorithms. The DIGNEA t... Read More about DIGNEA: A tool to generate diverse and discriminatory instance suites for optimisation domains.

Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches (2023)
Journal Article
Alissa, M., Sim, K., & Hart, E. (2023). Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches. Journal of Heuristics, 29(1), 1-38. https://doi.org/10.1007/s10732-022-09505-4

We propose a novel technique for algorithm-selection, applicable to optimisation domains in which there is implicit sequential information encapsulated in the data, e.g., in online bin-packing. Specifically we train two types of recurrent neural netw... Read More about Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches.

Evolutionary Approaches to Improving the Layouts of Instance-Spaces (2022)
Presentation / Conference Contribution
Sim, K., & Hart, E. (2022, September). Evolutionary Approaches to Improving the Layouts of Instance-Spaces. Presented at 17th International Conference, PPSN 2022, Dortmund, Germany

We propose two new methods for evolving the layout of an instance-space. Specifically we design three different fitness metrics that seek to: (i) reward layouts which place instances won by the same solver close in the space; (ii) reward layouts that... Read More about Evolutionary Approaches to Improving the Layouts of Instance-Spaces.

A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem (2022)
Presentation / Conference Contribution
Marrero, A., Segredo, E., León, C., & Hart, E. (2022, September). A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem. Presented at Parallel Problem Solving from Nature – PPSN XVII, 17th International Conference, Dortmund, Germany

We propose a new approach to generating synthetic instances in the knapsack domain in order to fill an instance-space. The method uses a novelty-search algorithm to search for instances that are diverse with respect to a feature-space but also elicit... Read More about A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem.

Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers (2022)
Presentation / Conference Contribution
Cardoso, R. P., Hart, E., Burth Kurka, D., & Pitt, J. (2022, April). Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers. Presented at EvoSTAR, Madrid

Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be comput... Read More about Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers.

Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn (2022)
Book Chapter
Hart, E. (2022). Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn. In A. E. Smith (Ed.), Women in Computational Intelligence: Key Advances and Perspectives on Emerging Topics (187-203). Springer. https://doi.org/10.1007/978-3-030-79092-9_9

Standard approaches to developing optimisation algorithms tend to involve selecting an algorithm and tuning it to work well on a large set of problem instances from the domain of interest. Once deployed, the algorithm remains static, failing to impro... Read More about Lifelong Learning Machines: Towards Developing Optimisation Systems That Continually Learn.

Morpho-evolution with learning using a controller archive as an inheritance mechanism (2022)
Journal Article
Le Goff, L. K., Buchanan, E., Hart, E., Eiben, A. E., Li, W., De Carlo, M., Winfield, A. F., Hale, M. F., Woolley, R., Angus, M., Timmis, J., & Tyrrell, A. M. (2023). Morpho-evolution with learning using a controller archive as an inheritance mechanism. IEEE Transactions on Cognitive and Developmental Systems, 15(2), 507-517. https://doi.org/10.1109/tcds.2022.3148543

Most work in evolutionary robotics centres on evolving a controller for a fixed body-plan. However, previous studiessuggest that simultaneously evolving both controller and body-plan could open up many interesting possibilities. However... Read More about Morpho-evolution with learning using a controller archive as an inheritance mechanism.

Artificial evolution of robot bodies and control: on the interaction between evolution, individual and cultural learning (2021)
Journal Article
Hart, E., & Le Goff, L. K. (2022). Artificial evolution of robot bodies and control: on the interaction between evolution, individual and cultural learning. Philosophical Transactions B: Biological Sciences, 377(1843), https://doi.org/10.1098/rstb.2021.0117

We survey and reflect on evolutionary approaches to the joint optimisation of the body and control of a robot, in scenarios where a the goal is to find a design that maximises performance on a specified task. The review is grounded in a general frame... Read More about Artificial evolution of robot bodies and control: on the interaction between evolution, individual and cultural learning.

Enhancing the practicality of tools to estimate the whole life embodied carbon of building structures via machine-learning models (2021)
Journal Article
Pomponi, F., Luque Anguita, M., Lange, M., D'Amico, B., & Hart, E. (2021). Enhancing the practicality of tools to estimate the whole life embodied carbon of building structures via machine-learning models. Frontiers in Built Environment, 7, Article 745598. https://doi.org/10.3389/fbuil.2021.745598

The construction and operation of buildings account for significant environmental impacts, including greenhouse gas (GHG) emissions, energy demand, resource consumption and waste generation. While the operation of buildings is fairly well regulated a... Read More about Enhancing the practicality of tools to estimate the whole life embodied carbon of building structures via machine-learning models.

A Neural Approach to Generation of Constructive Heuristics (2021)
Presentation / Conference Contribution
Alissa, M., Sim, K., & Hart, E. (2021, June). A Neural Approach to Generation of Constructive Heuristics. Presented at IEEE Congress on Evolutionary Computation 2021, Kraków, Poland (online)

Both algorithm-selection methods and hyper-heuristic methods rely on a pool of complementary heuristics. Improving the pool with new heuristics can improve performance, however, designing new heuristics can be challenging. Methods such as genetic pro... Read More about A Neural Approach to Generation of Constructive Heuristics.

A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics (2021)
Book Chapter
Stone, C., Hart, E., & Paechter, B. (2021). A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics. In N. Pillay, & R. Qu (Eds.), Automated Design of Machine Learning and Search Algorithms (91-107). Springer. https://doi.org/10.1007/978-3-030-72069-8_6

Hyper-heuristic frameworks, although intended to be cross-domain at the highest level, usually rely on a set of domain-specific low-level heuristics which exist below the domain-barrier and are manipulated by the hyper-heuristic itself. However, for... Read More about A Cross-Domain Method for Generation of Constructive and Perturbative Heuristics.

On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme (2021)
Presentation / Conference Contribution
Goff, L. K. L., & Hart, E. (2021, July). On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme. Presented at GECCO '21: Genetic and Evolutionary Computation Conference, Lille, France

We investigate a hierarchical scheme for the joint optimisation of robot bodies and controllers in a complex morphological space. An evolutionary algorithm optimises body-plans while a separate learning algorithm is applied to each body generated to... Read More about On the challenges of jointly optimising robot morphology and control using a hierarchical optimisation scheme.

Using novelty search to explicitly create diversity in ensembles of classifiers (2021)
Presentation / Conference Contribution
Cardoso, R. P., Hart, E., Kurka, D. B., & Pitt, J. V. (2021, July). Using novelty search to explicitly create diversity in ensembles of classifiers. Presented at GECCO '21: Genetic and Evolutionary Computation Conference, Lille, France [Online]

The diversity between individual learners in an ensemble is known to influence its performance. However, there is no standard agreement on how diversity should be defined, and thus how to exploit it to construct a high-performing classifier. We propo... Read More about Using novelty search to explicitly create diversity in ensembles of classifiers.