Abstract
Most modern solutions for video game balancing are directed towards specific games. We are currently researching general methods for automatic multiplayer game balancing. The problem is modeled as a meta-game, where game-play change the rules from another game. This way, a Machine Learning agent that learns to play a meta-game, learns how to change a base game following some balancing metric. But an issue resides in the generation of high volume of game-play training data, was agents of different skill compete against each other. For this end we propose the automatic generation of a population of surrogate agents by learning sampling. In Reinforcement Learning an agent learns in a trial error fashion where it improves gradually its policy, the mapping from world state to action to perform. This means that in each successful evolutionary step an agent follows a sub-optimal strategy, or eventually the optimal strategy. We store the agent policy at the end of each training episode. The process is evaluated in simple environments with distinct properties. Quality of the generated population is evaluated by the diversity of the difficulty the agents have in solving their tasks. © Springer Nature Switzerland AG 2019.

Abstract

From a digital culture perspective, this article has as main objective to assess two contemporary qualitative research methods in the field of education with distinct theoretical orientations: the cartographic method as a way of tracing trajectories in research-intervention with a theoretical basis in the biology of knowledge, enactive cognition and inventive cognition; and the cartographic method as a means of identifying and mapping the controversies linked to the different associations between human and non-human actors with a theoretical basis in actor-network theory (ANT). With their own specificities, both methods have been fruitful in the development of qualitative research in the field of education, in the context of digital culture, and more recently, in the hybrid culture of atopic habitation, mainly because they also relate to equally consistent theories and aspects of human cognition, making it possible to detect traces and clues in the fluid associations between actors enhanced by different digital technologies (DT), including data mining and learning analytics. From the Brazilian perspective on the topic, this article approaches the experience of the cartographic method of research intervention as well as the cartography of controversies as tools for developing qualitative research in education. These different forms of the cartographic method have inspired the construction of didactic-pedagogical experiences based on theoretical approaches linked to cognition, producing inventive methodologies and interventionist pedagogical practices. These methodologies and practices, which will be discussed at length in this article, have been developed and validated by the Research Group in Digital Education at Unisinos University at different levels and in varied educational settings.

Abstract
Future power system depends on penetrating more renewable energy to fulfill the drastic increase in energy demand with reduced carbon emission. Wind energy integration is increasing in worldwide each year. To efficiently investigate a quality voltage for AC loads under wind speed variations, a combined control strategy is proposed in this paper. It consists of PI and model predictive control (MPC) for the three-phase rectifier and interlinking inverter, respectively. The controlled rectifier ensures a constant DC-bus voltage under variable wind speed, while MPC is used to control output AC load voltage under abrupt load changes. Unlike traditional controllers, MPC does not require PI controllers for inner current and outer voltage loop or complex modulation steps. The discrete state-space model of VSI, LC filter, and load currents are used to predict future trends of load voltage for each of eight switching states. The control strategy selects the optimal switching state that reduces the error difference between reference and predicted load voltage. The proposed scheme is tested under perturbation of generation and load parameters. The proposed MPC strategy is compared with the conventional method-based PI controllers. The presented results ensure the effectiveness of the proposed approach with 0.67% THD for the AC output voltage.

Abstract
The internet is acknowledge as the main tourism communication medium and business facilitator. However, its functionality in this sector has been limited to e-commerce and focused on meeting the demand, thus underusing its potential as an essential tool for offer development, through the opportunities created by e-business. Since tourism is an eminently relational activity that strengthens itself from the sum of the joint efforts of its components, but oten fragmented and dispersed, this article advocates the adoption of online interorganizational collaboration platforms, which provides na environment for interactions, cooperation, and knowledge sharing amongst the social actors of tourist destinations. The proposal is based on the methodology of discourse analysis of extant literature on the internet economy and social network theory in tourism, exemplifying the advantages and difficulties that may arise from such a strategy. Recognizing that the available literature on this subject is scarce, three questions are also identified that can be tackled by future research.

Abstract
Diagnosis of Fabry disease (FD) remains a challenge mostly due to its rare occurrence and phenotipical variability, with considerable delay between onset and clinical diagnosis. It is then of extreme importance to explore biomarkers capable of assisting the earlier diagnosis of FD. There is growing evidence supporting the use of gait assessment in the diagnosis and management of several neurological diseases. In fact, gait abnormalities have previously been observed in FD, justifying further investigation. The aim of this study is to evaluate the effectiveness of different machine learning strategies when distinguishing patients with FD from healthy controls based on normalized gait features. Gait features of an individual are affected by physical characteristics including age, height, weight, and gender, as well as walking speed or stride length. Therefore, in order to reduce bias due to inter-subject variations a multiple regression (MR) normalization approach for gait data was performed. Four different machine learning strategies Support Vector Machines (SVM), Random Forest (RF), Multiple Layer Perceptrons (MLPs), and Deep Belief Networks (DBNs) - were employed on raw and normalized gait data. Wearable sensors positioned on both feet were used to acquire the gait data from 36 patients with FD and 34 healthy subjects. Gait normalization using MR revealed significant differences in percentage of stance phase spent in foot flat and pushing (p < 0.05), with FD presenting lower percentages in foot flat and higher in pushing. No significant differences were observed before gait normalization. Support Vector Machine was the superior classifier achieving an FD classification accuracy of 78.21 % after gait normalization, compared to 71.96% using raw gait data. Gait normalization improved the performance of all classifiers. To the best of our knowledge, this is the first study on gait classification that includes patients with FD, and our results support the use of gait assessment on the clinical assessment of FD.

Abstract
The recovery of walking function following spinal cord injury (SCI) is of major importance to patients and clinicians. In experimental SCI studies, a rat model is widely used to assess walking function, following thoracic spinal cord lesion. In an effort to provide a resource which investigators can refer to when seeking the most appropriate functional assay, the authors have compiled and categorized the behavioral assessments used to measure the deficits and recovery of the gait in thoracic SCI rats. These categories include kinematic and kinetic measurements. Within this categorization, we discuss the advantages and disadvantages of each type of measurement. The present review includes the type of outcome data that they produce, the technical difficulty and the time required to potentially train the animals to perform them, and the need for expensive or highly specialized equipment. The use of multiple kinematic and kinetic parameters is recommended to identify subtle deficits and processes involved in the compensatory mechanisms of walking function after experimental thoracic SCI in rats.