Pretrained Optimization Models (POMs) leverage knowledge gained from optimizing various tasks, providing efficient solutions for new optimization challenges through direct usage or fine-tuning. Despite the inefficiencies and limited generalization abilities observed in current POMs, our proposed model, the general pre-trained optimization model (GPOM), addresses these shortcomings. GPOM constructs a population-based pretrained Black-Box Optimization (BBO) model tailored for continuous optimization. Evaluation on the BBOB benchmark and two robot control tasks demonstrates that GPOM outperforms other pretrained BBO models significantly, especially for high-dimensional tasks. Its direct optimization performance exceeds that of state-of-the-art evolutionary algorithms and POMs. Furthermore, GPOM exhibits robust generalization capabilities across diverse task distributions, dimensions, population sizes, and optimization horizons.

For the robots to achieve a desired behavior, we can program them directly, train them, or give them an innate driver that makes the robots themselves desire the targeted behavior. With the minimal surprise approach, we implant in our robots the desire to make their world predictable. Here, we apply minimal surprise to collective construction. Simulated robots push blocks in a 2D torus grid world. In two variants of our experiment we either allow for emergent behaviors or predefine the expected environment of the robots. In either way, we evolve robot behaviors that move blocks to structure their environment and make it more predictable. The resulting controllers can be applied in collective construction by robots.

Applications of large-scale mobile multi-robot systems can be beneficial over monolithic robots because of higher potential for robustness and scalability. Developing controllers for multi-robot systems is challenging because the multitude of interactions is hard to anticipate and difficult to model. Automatic design using machine learning or evolutionary robotics seem to be options to avoid that challenge, but bring the challenge of designing reward or fitness functions. Generic reward and fitness functions seem unlikely to exist and task-specific rewards often have undesired side effects. Approaches of so-called innate motivation try to avoid the specific formulation of rewards and work instead with different drivers, such as curiosity. Our approach to innate motivation is to minimize surprise, which we implement by maximizing the accuracy of the swarm robot's sensor predictions using neuroevolution. A unique advantage of the swarm robot case is that swarm members populate the robot's environment and can trigger more active behaviors in a self-referential loop. We summarize our previous simulation-based results concerning behavioral diversity, robustness, scalability, and engineered self-organization, and put them into context. In several new studies, we analyze the influence of the optimizer's hyperparameters, the scalability of evolved behaviors, and the impact of realistic robot simulations. Finally, we present results using real robots that show how the reality gap can be bridged.

Analytical models developed in offline settings with pre-prepared data are typically used to predict students' performance. However, when data are available over time, this learning method is not suitable anymore. Online learning is increasingly used to update the online models from stream data. A rehearsal technique is typically used, which entails re-training the model on a small training set that is updated each time new data is received. The main challenge in this regard is the construction of the training set with appropriate data samples to maintain good model performance. Typically, a random selection of samples is made, which can deteriorate the model's performance. In this paper, we propose a memory-based online incremental learning approach for updating an online classifier that predicts student performance using stream data. The approach is based on the use of the genetic algorithm heuristic while respecting the memory space constraints as well as the balance of class labels. In contrast to random selection, our approach improves the stability of the analytical model by promoting diversity when creating the training set. As a proof of concept, we applied it to the open dataset OULAD. Our approach achieves a notable improvement in model accuracy, with an enhancement of nearly 10% compared to the current state-of-the-art, while maintaining a relatively low standard deviation in accuracy, ranging from 1% to 2.1%.

Collective decision-making enables multi-robot systems to act autonomously in real-world environments. Existing collective decision-making mechanisms suffer from the so-called speed versus accuracy trade-off or rely on high complexity, e.g., by including global communication. Recent work has shown that more efficient collective decision-making mechanisms based on artificial neural networks can be generated using methods from evolutionary computation. A major drawback of these decision-making neural networks is their limited interpretability. Analyzing evolved decision-making mechanisms can help us improve the efficiency of hand-coded decision-making mechanisms while maintaining a higher interpretability. In this paper, we analyze evolved collective decision-making mechanisms in detail and hand-code two new decision-making mechanisms based on the insights gained. In benchmark experiments, we show that the newly implemented collective decision-making mechanisms are more efficient than the state-of-the-art collective decision-making mechanisms voter model and majority rule.

Robotic applications across industries demand advanced navigation for safe and smooth movement. Smooth path planning is crucial for mobile robots to ensure stable and efficient navigation, as it minimizes jerky movements and enhances overall performance Achieving this requires smooth collision-free paths. Partial Swarm Optimization (PSO) and Potential Field (PF) are notable path-planning techniques, however, they may struggle to produce smooth paths due to their inherent algorithms, potentially leading to suboptimal robot motion and increased energy consumption. In addition, while PSO efficiently explores solution spaces, it generates long paths and has limited global search. On the contrary, PF methods offer concise paths but struggle with distant targets or obstacles. To address this, we propose Smoothed Partial Swarm Optimization with Improved Potential Field (SPSO-IPF), combining both approaches and it is capable of generating a smooth and safe path. Our research demonstrates SPSO-IPF's superiority, proving its effectiveness in static and dynamic environments compared to a mere PSO or a mere PF approach.

Unambiguous identification of the rewards driving behaviours of entities operating in complex open-ended real-world environments is difficult, partly because goals and associated behaviours emerge endogenously and are dynamically updated as environments change. Reproducing such dynamics in models would be useful in many domains, particularly where fixed reward functions limit the adaptive capabilities of agents. Simulation experiments described assess a candidate algorithm for the dynamic updating of rewards, RULE: Reward Updating through Learning and Expectation. The approach is tested in a simplified ecosystem-like setting where experiments challenge entities' survival, calling for significant behavioural change. The population of entities successfully demonstrate the abandonment of an initially rewarded but ultimately detrimental behaviour, amplification of beneficial behaviour, and appropriate responses to novel items added to their environment. These adjustment happen through endogenous modification of the entities' underlying reward function, during continuous learning, without external intervention.

Evolutionary Algorithms (EAs) play a crucial role in the architectural configuration and training of Artificial Deep Neural Networks (DNNs), a process known as neuroevolution. However, neuroevolution is hindered by its inherent computational expense, requiring multiple generations, a large population, and numerous epochs. The most computationally intensive aspect lies in evaluating the fitness function of a single candidate solution. To address this challenge, we employ Surrogate-assisted EAs (SAEAs). While a few SAEAs approaches have been proposed in neuroevolution, none have been applied to truly large DNNs due to issues like intractable information usage. In this work, drawing inspiration from Genetic Programming semantics, we use phenotypic distance vectors, outputted from DNNs, alongside Kriging Partial Least Squares (KPLS), an approach that is effective in handling these large vectors, making them suitable for search. Our proposed approach, named Neuro-Linear Genetic Programming surrogate model (NeuroLGP-SM), efficiently and accurately estimates DNN fitness without the need for complete evaluations. NeuroLGP-SM demonstrates competitive or superior results compared to 12 other methods, including NeuroLGP without SM, convolutional neural networks, support vector machines, and autoencoders. Additionally, it is worth noting that NeuroLGP-SM is 25% more energy-efficient than its NeuroLGP counterpart. This efficiency advantage adds to the overall appeal of our proposed NeuroLGP-SM in optimising the configuration of large DNNs.

Evolution Strategies (ES) have emerged as a competitive alternative for model-free reinforcement learning, showcasing exemplary performance in tasks like Mujoco and Atari. Notably, they shine in scenarios with imperfect reward functions, making them invaluable for real-world applications where dense reward signals may be elusive. Yet, an inherent assumption in ES, that all input features are task-relevant, poses challenges, especially when confronted with irrelevant features common in real-world problems. This work scrutinizes this limitation, particularly focusing on the Natural Evolution Strategies (NES) variant. We propose NESHT, a novel approach that integrates Hard-Thresholding (HT) with NES to champion sparsity, ensuring only pertinent features are employed. Backed by rigorous analysis and empirical tests, NESHT demonstrates its promise in mitigating the pitfalls of irrelevant features and shines in complex decision-making problems like noisy Mujoco and Atari tasks.

Containerization technology plays a crucial role in Federated Learning (FL) setups, expanding the pool of potential clients and ensuring the availability of specific subsets for each learning iteration. However, doubts arise about the trustworthiness of devices deployed as clients in FL scenarios, especially when container deployment processes are involved. Addressing these challenges is important, particularly in managing potentially malicious clients capable of disrupting the learning process or compromising the entire model. In our research, we are motivated to integrate a trust element into the client selection and model deployment processes within our system architecture. This is a feature lacking in the initial client selection and deployment mechanism of the On-Demand architecture. We introduce a trust mechanism, named "Trusted-On-Demand-FL", which establishes a relationship of trust between the server and the pool of eligible clients. Utilizing Docker in our deployment strategy enables us to monitor and validate participant actions effectively, ensuring strict adherence to agreed-upon protocols while strengthening defenses against unauthorized data access or tampering. Our simulations rely on a continuous user behavior dataset, deploying an optimization model powered by a genetic algorithm to efficiently select clients for participation. By assigning trust values to individual clients and dynamically adjusting these values, combined with penalizing malicious clients through decreased trust scores, our proposed framework identifies and isolates harmful clients. This approach not only reduces disruptions to regular rounds but also minimizes instances of round dismissal, Consequently enhancing both system stability and security.