Search-based procedural content generation (PCG) is a well-known method for level generation in games. Its key advantage is that it is generic and able to satisfy functional constraints. However, due to the heavy computational costs to run these algorithms online, search-based PCG is rarely utilized for real-time generation. In this paper, we introduce mutation models, a new type of iterative level generator based on machine learning. We train a model to imitate the evolutionary process and use the trained model to generate levels. This trained model is able to modify noisy levels sequentially to create better levels without the need for a fitness function during inference. We evaluate our trained models on a 2D maze generation task. We compare several different versions of the method: training the models either at the end of evolution (normal evolution) or every 100 generations (assisted evolution) and using the model as a mutation function during evolution. Using the assisted evolution process, the final trained models are able to generate mazes with a success rate of 99% and high diversity of 86%. The trained model is many times faster than the evolutionary process it was trained on. This work opens the door to a new way of learning level generators guided by an evolutionary process, meaning automatic creation of generators with specifiable constraints and objectives that are fast enough for runtime deployment in games.

Nature is an inhabitant for enormous number of species. All the species do perform complex activities with simple and elegant rules for their survival. The property of emergence of collective behavior is remarkably supporting their activities. One form of the collective behaviour is the swarm intelligence -- all agents poses same rules and capabilities. This equality along with local cooperation in the agents tremendously leads to achieving global results. Some of the swarm behaviours in the nature includes birds formations , fish school maneuverings, ants movement. Recently, one school of research has studied these behaviours and proposed artificial paradigms such as Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Glowworm Swarm Optimization (GSO) etc. Another school of research used these models and designed robotic platforms to detect (locate) multiple signal sources such as light, fire, plume, odour etc. Kinbots platform is one such recent experiment. In the same line of thought, this extended abstract presents the recently proposed butterfly inspired metaphor and corresponding simulations, ongoing experiments with outcomes.

Formation control problem is one of the most concerned topics within the realm of swarm intelligence, which is usually solved by conventional mathematical approaches. In this paper, however, we presents a metaheuristic approach that leverages a natural co-evolutionary strategy to solve the formation control problem for a swarm of missiles. The missile swarm is modeled by a second-order system with heterogeneous reference target, and exponential error function is made to be the objective function such that the swarm converge to optimal equilibrium states satisfying certain formation requirements. Focusing on the issue of local optimum and unstable evolution, we incorporate a novel model-based policy constraint and a population adaptation strategies that greatly alleviates the performance degradation. With application of the Molloy-Reed criterion in the field of network communication, we developed an adaptive topology method that assure the connectivity under node failure and its effectiveness are validated both theoretically and experimentally. Experimental results valid the effectiveness of the proposed formation control approach. More significantly, we showed that it is feasible to treat generic formation control problem as Markov Decision Process(MDP) and solve it through iterative learning.

Systematic development of accurate density functionals has been a decades-long challenge for scientists. Despite the emerging application of machine learning (ML) in approximating functionals, the resulting ML functionals usually contain more than tens of thousands parameters, which makes a huge gap in the formulation with the conventional human-designed symbolic functionals. We propose a new framework, Symbolic Functional Evolutionary Search (SyFES), that automatically constructs accurate functionals in the symbolic form, which is more explainable to humans, cheaper to evaluate, and easier to integrate to existing density functional theory codes than other ML functionals. We first show that without prior knowledge, SyFES reconstructed a known functional from scratch. We then demonstrate that evolving from an existing functional $\omega$B97M-V, SyFES found a new functional, GAS22 (Google Accelerated Science 22), that performs better for the majority of molecular types in the test set of Main Group Chemistry Database (MGCDB84). Our framework opens a new direction in leveraging computing power for the systematic development of symbolic density functionals.

In 1959, Arthur Samuel, a pioneer in the field of Artificial Intelligence defined the term Machine Learning [1] as the "field of study that gives computers the ability to learn without being explicitly programmed". In the field of Machine Learning, an important technique called Deep Learning allows "computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction" [2]. In recent years, many accurate decision support systems based on Deep Learning have been constructed as black boxes [3], that is as systems that hide their internal logic to the user. Thus, the purpose of an Explainable Artificial Intelligence [4-7] system is to make its behavior more intelligible to humans by providing explanations [8]. A popular approach to addressing the problem of opacity of black-box machine learning models is the use of post-hoc explainability methods: these methods approximate the logic of underlying machine learning models with the aim of explaining their internal workings, so that the user can understand them [9]. Unfortunately, these methods provide explanations that are not faithful to what the black-box model computes and can be misleading [10]. A recent and highly cited perspective [10] highlighted the need for white box models (i.e.

This paper seeks to answer the following question: \textit{"What can we learn by predicting accuracy?"}. Indeed, classification is one of the most popular tasks in machine learning, and many loss functions have been developed to maximize this non-differentiable objective function. Unlike past work on loss function design, which was guided mainly by intuition and theory before being validated by experimentation, here we propose to approach this problem in the opposite way: we seek to extract knowledge by experimentation. This data-driven approach is similar to that used in physics to discover general laws from data. We used a symbolic regression method to automatically find a mathematical expression highly correlated with a linear classifier's accuracy. The formula discovered on more than 260 datasets of embeddings has a Pearson's correlation of 0.96 and a $r^2$ of 0.93. More interestingly, this formula is highly explainable and confirms insights from various previous papers on loss design. We hope this work will open new perspectives in the search for new heuristics leading to a deeper understanding of machine learning theory.

An increasingly common area of study in procedural content generation is the creation of level segments: short pieces that can be used to form larger levels. Previous work has used basic concatenation to form these larger levels. However, even if the segments themselves are completable and well-formed, concatenation can fail to produce levels that are completable and can cause broken in-game structures (e.g. malformed pipes in Mario). We show this with three tile-based games: a side-scrolling platformer, a vertical platformer, and a top-down roguelike. Additionally, we present a Markov chain and a tree search algorithm that finds a link between two level segments, which uses filters to ensure completability and unbroken in-game structures in the linked segments. We further show that these links work well for multi-segment levels. We find that this method reliably finds links between segments and is customizable to meet a designer's needs.

Lexicase selection is a semantic-aware parent selection method, which assesses individual test cases in a randomly-shuffled data stream. It has demonstrated success in multiple research areas including genetic programming, genetic algorithms, and more recently symbolic regression and deep learning. One potential drawback of lexicase selection and its variants is that the selection procedure requires evaluating training cases in a single data stream, making it difficult to handle tasks where the evaluation is computationally heavy or the dataset is large-scale, e.g., deep learning. In this work, we investigate how the weighted shuffle methods can be employed to improve the efficiency of lexicase selection. We propose a novel method, fast lexicase selection, which incorporates lexicase selection and weighted shuffle with partial evaluation. Experiments on both classic genetic programming and deep learning tasks indicate that the proposed method can significantly reduce the number of evaluation steps needed for lexicase selection to select an individual, improving its efficiency while maintaining the performance.

Genetic Algorithm is a search based optimization algorithm used to solve problems were traditional methods fails. Genetic Algorithm is a search based optimization algorithm used to solve problems were traditional methods fails. It is an randomized algorithm where each step follows randomization principle. Genetic Algorithm was developed by John Holland, from the University of Michigan, in 1960. He proposed this algorithm based on the Charles Darwin's theory on Evolution of organism.

The rapid rise of machine learning and artificial intelligence has resulted in a mass of complex computational and operational challenges that some engineers are trying to tackle with evolutionary algorithms, which work towards multiple optimization objectives concurrently. Industrial Al company NNAISENSE has developed an open-source platform which leverages evolutionary algorithms as the building blocks for cascading machine learning challenges, helping spur industry growth. The platform, called EvoTorch, provides a software tool set that enables developers to experiment with evolutionary algorithms at any scale, without worrying about underlying details. The platform, built on the popular PyTorch and Ray packages, can create evolutionary algorithms that can be parallelized across CPUs or GPUs with little additional effort. "EvoTorch was conceived about five years ago, when the idea came to us to apply evolutionary algorithms to industrial projects and address the intricate challenges associated with scaling." said Dr. Timothy Atkinson, Research Scientist at NNAISENSE, in an interview with Design News.