Related papers: QED: using Quality-Environment-Diversity to evolve…

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

A novel two-dimensional (2D) learning framework has been proposed to address the feature selection problem in Power Quality (PQ) events. Unlike the existing feature selection approaches, the proposed 2D learning explicitly incorporates the…

Swarm robotics is a promising approach for the coordination of large numbers of robots. While previous studies have shown that evolutionary robotics techniques can be applied to obtain robust and efficient self-organized behaviors for robot…

Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To…

Prototyping robotic systems is a time consuming process. Computer aided design, however, might speed up the process significantly. Quality-diversity evolutionary approaches optimise for novelty as well as performance, and can be used to…

We propose a hybrid machine learning architecture that simultaneously employs multiple deep learning models analyzing contextual and behavioral characteristics of Windows portable executable, producing a final prediction based on a decision…

Quality Diversity (QD) algorithms such as MAP-Elites are a class of optimisation techniques that attempt to find many high performing points that all behave differently according to a user-defined behavioural metric. In this paper we…

Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the…

Many swarm robotics tasks consist of multiple conflicting objectives. This research proposes a multi-objective evolutionary neural network approach to developing controllers for swarms of robots. The swarm robot controllers are trained in a…

We present DEI: Diversity in Evolutionary Inference, a distributed Quality-Diversity (QD) search framework that assigns heterogeneous large language models (LLMs) as mutation operators across peer nodes communicating with non-blocking…

A core challenge of evolutionary search is the need to balance between exploration of the search space and exploitation of highly fit regions. Quality-diversity search has explicitly walked this tightrope between a population's diversity…

Domain-specific quantitative reasoning remains a major challenge for large language models (LLMs), especially in fields requiring expert knowledge and complex question answering (QA). In this work, we propose Expert Question Decomposition…

Marine obstacle detection demands robust segmentation under challenging conditions, such as sun glitter, fog, and rapidly changing wave patterns. These factors degrade image quality, while the scarcity and structural repetition of marine…

Swarms of drones are gaining more and more autonomy and efficiency during their missions. However, security threats can disrupt their missions' progression. To overcome this problem, Network Intrusion Detection Systems ((N)IDS) are…

Communication is a vital component for all swarm robotics applications, and even simple swarm robotics behaviours often break down when this communication is unreliable. Since wireless communications are inherently subject to interference…

Uncertainty quantification (UQ) is the process of systematically determining and characterizing the degree of confidence in computational model predictions. In the context of systems biology, especially with dynamic models, UQ is crucial…

We theoretically explore the relationship between sample-efficiency and adaptivity in reinforcement learning. An algorithm is sample-efficient if it uses a number of queries $n$ to the environment that is polynomial in the dimension $d$ of…

Predicting and executing a sequence of actions without intermediate replanning, known as action chunking, is increasingly used in robot learning from human demonstrations. Yet, its effects on the learned policy remain inconsistent: some…

Experimental design techniques such as active search and Bayesian optimization are widely used in the natural sciences for data collection and discovery. However, existing techniques tend to favor exploitation over exploration of the search…

Robots must balance compliance with safety and social expectations as blind obedience can cause harm, while over-refusal erodes trust. Existing safe reinforcement learning (RL) benchmarks emphasize physical hazards, while human-robot…