A Systematic Literature Review of the Successors of "NeuroEvolution of Augmenting Topologies"

Improving the performance of mutation-based evolving artificial neural networks with self-adaptive mutations

Neuroevolution is a promising approach for designing artificial neural networks using an evolutionary algorithm. Unlike recent trending methods that rely on gradient-based algorithms, neuroevolution can simultaneously evolve the topology and weights of neural networks. In neuroevolution with topological evolution, handling crossover is challenging because of the competing conventions problem. Mutation-based evolving artificial neural network is an alternative topology and weights neuroevolution approach that omits crossover and uses only mutations for genetic variation. This study enhances the performance of mutation-based evolving artificial neural network in two ways. First, the mutation step size controlling the magnitude of the parameter perturbation is automatically adjusted by a self-adaptive mutation mechanism, enabling a balance between exploration and exploitation during the evolution process. Second, the structural mutation probabilities are automatically adjusted depending on the network size, preventing excessive expansion of the topology. The proposed methods are compared with conventional neuroevolution algorithms using locomotion tasks provided in the OpenAI Gym benchmarks. The results demonstrate that the proposed methods with the self-adaptive mutation mechanism can achieve better performance. In addition, the adjustment of structural mutation probabilities can mitigate topological bloat while maintaining performance.

Reinforcement learned adversarial agent (ReLAA) for active fault detection and prediction in space habitats

With growing interest for human space tourism in the twenty-first century, much attention has been directed to the robust engineering of Environmental Control and Life Support Systems in space habitats. The stable, reliable operation of such a habitat is partly achieved with an ability to recognize and predict faults. For these two purposes, a reinforcement learning adversarial agent (ReLAA) is utilized in this work. A ReLAA is trained with experimental data to actively recognize and predict faults. These capabilities are achieved by proposing actions that activate known faults in a system. Instead of issuing these harmful actions to the actual hardware, a digital twin of the mock space habitat is simulated to discover vulnerabilities that would lead to faulted operation. The methods developed in this work will allow for the discovery of damaging latent behavior, and the reduction of false positive and negative fault identification.

Explaining the Neuroevolution of Fighting Creatures Through Virtual fMRI

While interest in artificial neural networks (ANNs) has been renewed by the ubiquitous use of deep learning to solve high-dimensional problems, we are still far from general artificial intelligence. In this article, we address the problem of emergent cognitive capabilities and, more crucially, of their detection, by relying on co-evolving creatures with mutable morphology and neural structure. The former is implemented via both static and mobile structures whose shapes are controlled by cubic splines. The latter uses ESHyperNEAT to discover not only appropriate combinations of connections and weights but also to extrapolate hidden neuron distribution. The creatures integrate low-level perceptions (touch/pain proprioceptors, retina-based vision, frequency-based hearing) to inform their actions. By discovering a functional mapping between individual neurons and specific stimuli, we extract a high-level module-based abstraction of a creature's brain. This drastically simplifies the discovery of relationships between naturally occurring events and their neural implementation. Applying this methodology to creatures resulting from solitary and tag-team co-evolution showed remarkable dynamics such as range-finding and structured communication. Such discovery was made possible by the abstraction provided by the modular ANN which allowed groups of neurons to be viewed as functionally enclosed entities.

Evolving neural networks through bio-inspired parent selection in dynamic environments

Environmental variability often degrades the performance of algorithms designed to capture the global convergence of a given search space. Several approaches have been developed to challenge environmental uncertainty by incorporating biologically inspired notions, focusing on crossover, mutation, and selection. This study proposes a bio-inspired approach called NEAT-HD, which focuses on parent selection based on genetic similarity. The originality of the proposed approach rests on its use of a sigmoid function to accelerate species formation and contribute to population diversity. Experiments on two classic control tasks were performed to demonstrate the performance of the proposed method. The results show that NEAT-HD can dynamically adapt to its environment by forming hybrid individuals originating from genetically distinct parents. Additionally, an increase in diversity within the population was observed due to the formation of hybrids and novel individuals, which has never been observed before. Comparing two tasks, the characteristics of NEAT-HD were improved by appropriately setting the algorithm to include the distribution of genetic distance within the population. Our key finding is the inherent potential of newly formed individuals for robustness against dynamic environments.