Outputs (96)

Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances (2024)
Presentation / Conference Contribution
Hart, E., Renau, Q., Sim, K., & Alissa, M. (2024, September). Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances. Presented at 18th International Conference on Parallel Problem Solving From Nature PPSN 2024, Hagenburg, Austria

Deep neural networks (DNN) are increasingly being used to perform algorithm-selection in combinatorial optimisation domains, particularly as they accommodate input representations which avoid designing and calculating features. Mounting evidence fro... Read More about Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances.

Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture (2024)
Presentation / Conference Contribution
Le Goff, L., & Hart, E. (2024, July). Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture. Presented at GECCO 2024 Embodied and Evolved Artificial Intelligence Workshop, Melbourne, Australia

Algorithmic frameworks for the joint optimisation of a robot's design and controller often utilise a learning loop nested within an evolutionary algorithm to refine the controller associated with a newly generated robot design. Intuitively, it is rea... Read More about Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture.

Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution (2024)
Presentation / Conference Contribution
Marrero, A., Segredo, E., León, C., & Hart, E. (2024, July). Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution. Presented at GECCO '24: Genetic and Evolutionary Computation Conference, Melbourne, Australia

The ability to generate example instances from a domain is important in order to benchmark algorithms and to generate data that covers an instance-space in order to train machine-learning models for algorithm selection. Quality-Diversity (QD) algorit... Read More about Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution.

Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, July). Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples. Presented at GECCO 2024, Melbourne, Australia

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajec-tories obtained from running a solver as input... Read More about Improving Algorithm-Selection and Performance-Prediction via Learning Discriminating Training Samples.

Automated Human-Readable Label Generation in Open Intent Discovery (2024)
Presentation / Conference Contribution
Anderson, G., Hart, E., Gkatzia, D., & Beaver, I. (2024, September). Automated Human-Readable Label Generation in Open Intent Discovery. Presented at Interspeech 2024, Kos, Greece

The correct determination of user intent is key in dialog systems. However, an intent classifier often requires a large, labelled training dataset to identify a set of known intents. The creation of such a dataset is a complex and time-consuming task... Read More about Automated Human-Readable Label Generation in Open Intent Discovery.

Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains (2024)
Journal Article
Marrero, A., Segredo, E., Leon, C., & Hart, E. (online). Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains. Evolutionary Computation, https://doi.org/10.1162/evco_a_00350

Gathering sufficient instance data to either train algorithm-selection models or understand algorithm footprints within an instance space can be challenging. We propose an approach to generating synthetic instances that are tailored to perform well w... Read More about Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains.

An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation (2024)
Presentation / Conference Contribution
Stone, C., Renau, Q., Miguel, I., & Hart, E. (2024, June). An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation. Presented at 18TH LEARNING AND INTELLIGENT OPTIMIZATION CONFERENCE, Ischia, Italy

We address the question of multi-task algorithm selection in combinatorial optimisation domains. This is motivated by a desire to simplify the algorithm-selection pipeline by developing a more general classifier that does not require specialised info... Read More about An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation.

A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control (2024)
Presentation / Conference Contribution
Montague, K., Hart, E., & Paechter, B. (2024, April). A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control. Presented at EvoStar 2024, Aberystwyth

Behaviour trees (BTs) are commonly used as controllers in robotic swarms due their modular composition and to the fact that they can be easily interpreted by humans. From an algorithmic perspective, an additional advantage is that extra modules can e... Read More about A Hierarchical Approach to Evolving Behaviour-Trees for Swarm Control.

On the Utility of Probing Trajectories for Algorithm-Selection (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, April). On the Utility of Probing Trajectories for Algorithm-Selection. Presented at EvoStar 2024, Aberystwyth, UK

Machine-learning approaches to algorithm-selection typically take data describing an instance as input. Input data can take the form of features derived from the instance description or fitness landscape , or can be a direct representation of the ins... Read More about On the Utility of Probing Trajectories for Algorithm-Selection.

Generalized Early Stopping in Evolutionary Direct Policy Search (2024)
Journal Article
Arza, E., Le Goff, L. K., & Hart, E. (2024). Generalized Early Stopping in Evolutionary Direct Policy Search. ACM Transactions on Evolutionary Learning and Optimization, 4(3), Article 14. https://doi.org/10.1145/3653024

Lengthy evaluation times are common in many optimization problems such as direct policy search tasks, especially when they involve conducting evaluations in the physical world, e.g. in robotics applications. Often when evaluating solution over a fixe... Read More about Generalized Early Stopping in Evolutionary Direct Policy Search.

Evolving Behavior Allocations in Robot Swarms (2024)
Presentation / Conference Contribution
Hallauer, S., Nitschke, G., & Hart, E. (2023, December). Evolving Behavior Allocations in Robot Swarms. Presented at IEEE Symposium Series on Computational Intelligence (SSCI 2023), Mexico City, Mexico

Behavioral diversity is known to benefit problem-solving in biological social systems such as insect colonies and human societies, as well as in artificial distributed systems including large-scale software and swarm-robotics systems. We investigate... Read More about Evolving Behavior Allocations in Robot Swarms.

Evaluation of Frameworks That Combine Evolution and Learning to Design Robots in Complex Morphological Spaces (2023)
Journal Article
Li, W., Buchanan, E., Goff, L. K. L., Hart, E., Hale, M. F., Wei, B., Carlo, M. D., Angus, M., Woolley, R., Gan, Z., Winfield, A. F., Timmis, J., Eiben, A. E., & Tyrrell, A. M. (online). Evaluation of Frameworks That Combine Evolution and Learning to Design Robots in Complex Morphological Spaces. IEEE Transactions on Evolutionary Computation, https://doi.org/10.1109/tevc.2023.3316363

Jointly optimising both the body and brain of a robot is known to be a challenging task, especially when attempting to evolve designs in simulation that will subsequently be built in the real world. To address this, it is increasingly common to combi... Read More about Evaluation of Frameworks That Combine Evolution and Learning to Design Robots in Complex Morphological Spaces.

Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity (2023)
Preprint / Working Paper
Pringle, S., Davies, Z. G., Goddard, M. A., Dallimer, M., Hart, E., Le Goff, L., & Langdale, S. J. (2023). Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity

Welcome to the UK-RAS White paper Series on Robotics and Autonomous Systems (RAS). This is one of the core activities of UK-RAS Network, funded by the Engineering and Physical Sciences Research Council (EPSRC). By Bringing together academic centres o... Read More about Robotics and Autonomous Systems for Environmental Sustainability: Monitoring Terrestrial Biodiversity.

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.

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.

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.

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.

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.